@basetenlabs/client - v0.2.0
    Preparing search index...

    Type Alias components

    This file was auto-generated by openapi-typescript. Do not make direct changes to the file.

    type components = {
        headers: never;
        parameters: {
            api_key_prefix: string;
            chain_deployment_id: string;
            chain_id: string;
            chainlet_id: string;
            checkpoint_id: string;
            deployment_id: string;
            endpoint_id: string;
            env_name: string;
            group_id: string;
            model_api_name: string;
            model_id: string;
            replica_id: string;
            run_id: string;
            sampler_id: string;
            secret_name: string;
            session_id: string;
            team_id: string;
            training_job_id: string;
            training_project_id: string;
            user_defined_listing_id: string;
            user_id: string;
            version_tag: string;
            volume_name: string;
            volume_namespace: string;
            volume_version: string;
        };
        pathItems: never;
        requestBodies: never;
        responses: never;
        schemas: {
            ActivateResponse: { no_op: boolean; success: boolean };
            ActiveJobAtSubmit: {
                instance_type_name: string;
                status_at_submit: string;
                status_set_at: string;
                total_gpus: number;
                training_job_id: string;
                training_job_name: string | null;
                workload_plane_name: string;
            };
            APIKey: { api_key: string };
            APIKeyCategory:
                | "PERSONAL"
                | "ROUTES"
                | "WORKSPACE_MANAGE_ALL"
                | "WORKSPACE_EXPORT_METRICS"
                | "WORKSPACE_INVOKE"
                | "WORKSPACE_MANAGE_API_KEYS";
            APIKeyInfo: {
                model_ids: string[]
                | null;
                name: string | null;
                owner: components["schemas"]["APIKeyOwner"] | null;
                prefix: string;
                team_name: string | null;
                type: components["schemas"]["APIKeyCategory"];
            };
            APIKeyOwner: {
                email: string
                | null;
                name: string | null;
                user_id: string;
            };
            APIKeys: { keys: components["schemas"]["APIKeyInfo"][] };
            APIKeyTombstone: { prefix: string };
            AuditLogActor: {
                api_key_name: string | null;
                api_key_prefix: string | null;
                email: string | null;
                type: components["schemas"]["AuditLogActorType"];
            };
            AuditLogActorType: | "USER"
            | "API_KEY"
            | "BASETEN_USER"
            | "BASETEN_SYSTEM"
            | "TOMBSTONE_USER";
            AuditLogApiKeyType: | "PERSONAL"
            | "CREATOR_SERVICE_ACCOUNT"
            | "MANAGE_API_KEYS_SERVICE_ACCOUNT"
            | "INVOKE_ALL_MODELS_SERVICE_ACCOUNT"
            | "INVOKE_ALLOWED_MODELS_SERVICE_ACCOUNT"
            | "INVOKE_SCOPED_ENVS_AND_MODELS_SERVICE_ACCOUNT"
            | "EXPORT_METRICS_ALL_MODELS_SERVICE_ACCOUNT"
            | "EXPORT_METRICS_ALLOWED_MODELS_SERVICE_ACCOUNT"
            | "INVOKE_ALL_SHARED_ENDPOINTS_SERVICE_ACCOUNT"
            | "INVOKE_ALLOWED_SHARED_ENDPOINTS_SERVICE_ACCOUNT"
            | "INVOKE_ALL_ROUTES";
            AuditLogEntry: {
                actor: components["schemas"]["AuditLogActor"];
                client_name: string
                | null;
                client_session_id: string | null;
                client_version: string | null;
                created: string;
                event_data:
                    | components["schemas"]["AuditLogEventModelDeployed"]
                    | components["schemas"]["AuditLogEventModelDeploymentActivated"]
                    | components["schemas"]["AuditLogEventModelDeploymentDeactivated"]
                    | components["schemas"]["AuditLogEventModelDeploymentRetried"]
                    | components["schemas"]["AuditLogEventModelDeploymentPromoted"]
                    | components["schemas"]["AuditLogEventModelDeploymentAutoscalingSettingsChanged"]
                    | components["schemas"]["AuditLogEventModelDeploymentRequestBackpressureSettingsChanged"]
                    | components["schemas"]["AuditLogEventModelDeploymentInstanceTypeChanged"]
                    | components["schemas"]["AuditLogEventModelDeploymentDeleted"]
                    | components["schemas"]["AuditLogEventModelDeleted"]
                    | components["schemas"]["AuditLogEventChainDeployed"]
                    | components["schemas"]["AuditLogEventChainDeploymentActivated"]
                    | components["schemas"]["AuditLogEventChainDeploymentDeactivated"]
                    | components["schemas"]["AuditLogEventChainDeploymentPromoted"]
                    | components["schemas"]["AuditLogEventChainletAutoscalingSettingsChanged"]
                    | components["schemas"]["AuditLogEventChainletInstanceTypeChanged"]
                    | components["schemas"]["AuditLogEventChainDeploymentDeleted"]
                    | components["schemas"]["AuditLogEventChainDeleted"]
                    | components["schemas"]["AuditLogEventChainEnvironmentCreated"]
                    | components["schemas"]["AuditLogEventChainEnvironmentUpdated"]
                    | components["schemas"]["AuditLogEventSecretUpdated"]
                    | components["schemas"]["AuditLogEventSecretDeleted"]
                    | components["schemas"]["AuditLogEventApiKeyCreated"]
                    | components["schemas"]["AuditLogEventApiKeyDeleted"]
                    | components["schemas"]["AuditLogEventGatewayEndpointCreated"]
                    | components["schemas"]["AuditLogEventGatewayEndpointUpdated"]
                    | components["schemas"]["AuditLogEventGatewayEndpointDeleted"]
                    | components["schemas"]["AuditLogEventUserInvited"]
                    | components["schemas"]["AuditLogEventUserJoinedOrganization"]
                    | components["schemas"]["AuditLogEventWebhookSigningSecretCreated"]
                    | components["schemas"]["AuditLogEventWebhookSigningSecretRotated"]
                    | components["schemas"]["AuditLogEventWebhookSigningSecretDeleted"]
                    | components["schemas"]["AuditLogEventUserRoleUpdated"]
                    | components["schemas"]["AuditLogEventUserTeamRoleUpdated"]
                    | components["schemas"]["AuditLogEventUserRemoved"]
                    | components["schemas"]["AuditLogEventDirectoryGroupRoleUpdated"]
                    | components["schemas"]["AuditLogEventRequireGroupBasedAdminsEnabled"]
                    | components["schemas"]["AuditLogEventEnvironmentCreated"]
                    | components["schemas"]["AuditLogEventEnvironmentUpdated"]
                    | components["schemas"]["AuditLogEventEnvironmentDeleted"]
                    | components["schemas"]["AuditLogEventReplicaTerminated"]
                    | components["schemas"]["AuditLogEventModelPromotionControlAction"]
                    | components["schemas"]["AuditLogEventSshCertificateSigned"]
                    | components["schemas"]["AuditLogEventVolumeDeleted"]
                    | components["schemas"]["AuditLogEventVolumeVersionDeleted"]
                    | components["schemas"]["AuditLogEventVolumeVersionRestored"];
                event_type: components["schemas"]["AuditLogEventType"];
                id: string;
                source: components["schemas"]["AuditLogSource"]
                | null;
            };
            AuditLogEventApiKeyCreated: {
                api_key_id: string;
                api_key_type: components["schemas"]["AuditLogApiKeyType"];
                event_type: "API_KEY_CREATED";
                prefix: string;
            };
            AuditLogEventApiKeyDeleted: {
                api_key_id: string;
                api_key_type: components["schemas"]["AuditLogApiKeyType"];
                event_type: "API_KEY_DELETED";
                prefix: string;
            };
            AuditLogEventAutoscalingScheduleAction: | "CREATED"
            | "UPDATED"
            | "DELETED"
            | "UNCHANGED";
            AuditLogEventAutoscalingScheduleChange: {
                action: components["schemas"]["AuditLogEventAutoscalingScheduleAction"];
                current: | components["schemas"]["AuditLogEventAutoscalingScheduleSettings"]
                | null;
                previous: | components["schemas"]["AuditLogEventAutoscalingScheduleSettings"]
                | null;
                schedule_id: string;
            };
            AuditLogEventAutoscalingScheduleSettings: {
                autoscaling_window: number
                | null;
                cadence: string;
                concurrency_target: number | null;
                enabled: boolean;
                end_at: string | null;
                end_hour: number | null;
                end_minute: number | null;
                max_replica: number;
                max_scale_down_rate: number | null;
                min_replica: number;
                scale_down_delay: number | null;
                schedule_name: string;
                start_at: string | null;
                start_hour: number | null;
                start_minute: number | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
                timezone: string;
                weekdays: string[] | null;
            };
            AuditLogEventAutoscalingSettings: {
                autoscaling_window: number
                | null;
                concurrency_target: number;
                max_replica: number;
                max_scale_down_rate: number | null;
                min_replica: number;
                scale_down_delay: number | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AuditLogEventChainDeleted: {
                chain_deployment_name: string
                | null;
                chain_id: string;
                chain_name: string;
                event_type: "CHAIN_DELETED";
            };
            AuditLogEventChainDeployed: {
                chain_deployment_id: string;
                chain_deployment_name: string
                | null;
                chain_id: string;
                chain_name: string;
                event_type: "CHAIN_DEPLOYED";
                is_primary: boolean;
                publish: boolean;
            };
            AuditLogEventChainDeploymentActivated: {
                chain_deployment_id: string;
                chain_deployment_name: string
                | null;
                chain_id: string;
                chain_name: string;
                event_type: "CHAIN_DEPLOYMENT_ACTIVATED";
            };
            AuditLogEventChainDeploymentDeactivated: {
                chain_deployment_id: string;
                chain_deployment_name: string
                | null;
                chain_id: string;
                chain_name: string;
                event_type: "CHAIN_DEPLOYMENT_DEACTIVATED";
            };
            AuditLogEventChainDeploymentDeleted: {
                chain_deployment_id: string;
                chain_id: string;
                chain_name: string;
                deployment_name: string
                | null;
                event_type: "CHAIN_DEPLOYMENT_DELETED";
            };
            AuditLogEventChainDeploymentPromoted: {
                chain_deployment_id: string;
                chain_deployment_name: string
                | null;
                chain_id: string;
                chain_name: string;
                environment_id: string | null;
                environment_name: string | null;
                event_type: "CHAIN_DEPLOYMENT_PROMOTED";
            };
            AuditLogEventChainEnvironmentCreated: {
                chain_id: string;
                chain_name: string;
                environment_name: string;
                event_type: "CHAIN_ENVIRONMENT_CREATED";
                ramp_up_duration_seconds: number
                | null;
                ramp_up_while_promoting: boolean | null;
                redeploy_on_promotion: boolean | null;
            };
            AuditLogEventChainEnvironmentUpdated: {
                chain_id: string;
                chain_name: string;
                environment_name: string;
                event_type: "CHAIN_ENVIRONMENT_UPDATED";
                ramp_up_duration_seconds: number
                | null;
                ramp_up_while_promoting: boolean | null;
                redeploy_on_promotion: boolean | null;
            };
            AuditLogEventChainletAutoscalingSettingsChanged: {
                autoscaling_window: number
                | null;
                chain_deployment_id: string;
                chain_deployment_name: string | null;
                chain_id: string;
                chain_name: string;
                chainlet_id: string;
                chainlet_name: string;
                concurrency_target: number;
                event_type: "CHAINLET_AUTOSCALING_SETTINGS_CHANGED";
                max_replica: number;
                max_scale_down_rate: number | null;
                min_replica: number;
                previous_settings:
                    | components["schemas"]["AuditLogEventAutoscalingSettings"]
                    | null;
                scale_down_delay: number
                | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AuditLogEventChainletInstanceTypeChanged: {
                chain_deployment_id: string;
                chain_deployment_name: string
                | null;
                chain_id: string;
                chain_name: string;
                chainlet_id: string;
                chainlet_name: string;
                event_type: "CHAINLET_INSTANCE_TYPE_CHANGED";
                instance_type_name: string;
            };
            AuditLogEventDirectoryGroupRoleUpdated: {
                directory_group_id: string;
                directory_group_name: string;
                event_type: "DIRECTORY_GROUP_ROLE_UPDATED";
                new_role_name: string;
                team_id: string
                | null;
                team_name: string | null;
            };
            AuditLogEventEnvironmentCreated: {
                autoscaling_window: number
                | null;
                concurrency_target: number;
                deployment_type: string | null;
                environment_name: string;
                event_type: "ENVIRONMENT_CREATED";
                max_replica: number;
                max_scale_down_rate: number | null;
                max_surge_percent: number | null;
                max_unavailable_percent: number | null;
                min_replica: number;
                model_id: string;
                model_name: string;
                promotion_cleanup_strategy: string | null;
                ramp_up_duration_seconds: number | null;
                ramp_up_step_size: number | null;
                ramp_up_while_promoting: boolean | null;
                redeploy_on_promotion: boolean | null;
                replica_overhead_percent: number | null;
                request_backpressure_policy: string | null;
                rolling_deploy: boolean | null;
                rolling_deploy_strategy: string | null;
                scale_down_delay: number | null;
                stabilization_time_seconds: number | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AuditLogEventEnvironmentDeleted: {
                environment_name: string;
                event_type: "ENVIRONMENT_DELETED";
                model_id: string;
                model_name: string;
            };
            AuditLogEventEnvironmentSettings: {
                autoscaling_window: number
                | null;
                concurrency_target: number;
                max_replica: number;
                max_scale_down_rate: number | null;
                max_surge_percent: number | null;
                max_unavailable_percent: number | null;
                min_replica: number;
                promotion_cleanup_strategy: string | null;
                ramp_up_duration_seconds: number | null;
                ramp_up_step_size: number | null;
                ramp_up_while_promoting: boolean | null;
                redeploy_on_promotion: boolean | null;
                replica_overhead_percent: number | null;
                request_backpressure_policy: string | null;
                rolling_deploy: boolean | null;
                rolling_deploy_strategy: string | null;
                scale_down_delay: number | null;
                stabilization_time_seconds: number | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AuditLogEventEnvironmentUpdated: {
                autoscaling_window: number
                | null;
                concurrency_target: number;
                deployment_type: string | null;
                environment_name: string;
                event_type: "ENVIRONMENT_UPDATED";
                max_replica: number;
                max_scale_down_rate: number | null;
                max_surge_percent: number | null;
                max_unavailable_percent: number | null;
                min_replica: number;
                model_id: string;
                model_name: string;
                previous_settings:
                    | components["schemas"]["AuditLogEventEnvironmentSettings"]
                    | null;
                promotion_cleanup_strategy: string
                | null;
                ramp_up_duration_seconds: number | null;
                ramp_up_step_size: number | null;
                ramp_up_while_promoting: boolean | null;
                redeploy_on_promotion: boolean | null;
                replica_overhead_percent: number | null;
                request_backpressure_policy: string | null;
                rolling_deploy: boolean | null;
                rolling_deploy_strategy: string | null;
                scale_down_delay: number | null;
                schedules:
                    | components["schemas"]["AuditLogEventAutoscalingScheduleChange"][]
                    | null;
                stabilization_time_seconds: number
                | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AuditLogEventGatewayEndpointCreated: {
                event_type: "GATEWAY_ENDPOINT_CREATED";
                gateway_endpoint_id: string;
                slug: string;
            };
            AuditLogEventGatewayEndpointDeleted: {
                event_type: "GATEWAY_ENDPOINT_DELETED";
                gateway_endpoint_id: string;
                slug: string;
            };
            AuditLogEventGatewayEndpointUpdated: {
                event_type: "GATEWAY_ENDPOINT_UPDATED";
                gateway_endpoint_id: string;
                previous_slug: string
                | null;
                slug: string;
            };
            AuditLogEventModelDeleted: {
                event_type: "MODEL_DELETED";
                model_id: string;
                model_name: string;
            };
            AuditLogEventModelDeployed: {
                deployment_id: string;
                deployment_name: string;
                environment_name: string
                | null;
                event_type: "MODEL_DEPLOYED";
                model_id: string;
                model_name: string;
                publish: boolean;
                scale_previous_to_zero: boolean;
                trusted: boolean;
            };
            AuditLogEventModelDeploymentActivated: {
                deployment_id: string;
                deployment_name: string;
                event_type: "MODEL_DEPLOYMENT_ACTIVATED";
                model_id: string;
                model_name: string;
            };
            AuditLogEventModelDeploymentAutoscalingSettingsChanged: {
                autoscaling_window: number
                | null;
                concurrency_target: number;
                deployment_id: string;
                deployment_name: string;
                deployment_type: string | null;
                event_type: "MODEL_DEPLOYMENT_AUTOSCALING_SETTINGS_CHANGED";
                max_replica: number;
                max_scale_down_rate: number | null;
                min_replica: number;
                model_id: string;
                model_name: string;
                previous_settings:
                    | components["schemas"]["AuditLogEventAutoscalingSettings"]
                    | null;
                scale_down_delay: number
                | null;
                schedules:
                    | components["schemas"]["AuditLogEventAutoscalingScheduleChange"][]
                    | null;
                target_in_flight_tokens: number
                | null;
                target_utilization_percentage: number | null;
            };
            AuditLogEventModelDeploymentDeactivated: {
                deployment_id: string;
                deployment_name: string;
                event_type: "MODEL_DEPLOYMENT_DEACTIVATED";
                model_id: string;
                model_name: string;
            };
            AuditLogEventModelDeploymentDeleted: {
                deployment_id: string;
                deployment_name: string;
                event_type: "MODEL_DEPLOYMENT_DELETED";
                model_id: string;
                model_name: string;
            };
            AuditLogEventModelDeploymentInstanceTypeChanged: {
                deployment_id: string;
                deployment_name: string;
                event_type: "MODEL_DEPLOYMENT_INSTANCE_TYPE_CHANGED";
                instance_type_name: string;
                model_id: string;
                model_name: string;
            };
            AuditLogEventModelDeploymentPromoted: {
                deployment_id: string;
                deployment_name: string;
                environment_id: string
                | null;
                environment_name: string | null;
                event_type: "MODEL_DEPLOYMENT_PROMOTED";
                model_id: string;
                model_name: string;
            };
            AuditLogEventModelDeploymentRequestBackpressureSettingsChanged: {
                deployment_id: string;
                deployment_name: string;
                event_type: "MODEL_DEPLOYMENT_REQUEST_BACKPRESSURE_SETTINGS_CHANGED";
                model_id: string;
                model_name: string;
                policy: string
                | null;
                previous_policy: string | null;
            };
            AuditLogEventModelDeploymentRetried: {
                deployment_id: string;
                deployment_name: string;
                event_type: "MODEL_DEPLOYMENT_RETRIED";
                model_id: string;
                model_name: string;
                retried: boolean;
            };
            AuditLogEventModelPromotionControlAction: {
                action: components["schemas"]["AuditLogPromotionControlAction"];
                deployment_id: string;
                deployment_name: string;
                environment_id: string
                | null;
                environment_name: string;
                event_type: "MODEL_PROMOTION_CONTROL_ACTION";
                model_id: string;
                model_name: string;
            };
            AuditLogEventReplicaTerminated: {
                deployment_id: string;
                deployment_name: string;
                event_type: "REPLICA_TERMINATED";
                model_id: string;
                model_name: string;
                replica_id: string;
            };
            AuditLogEventRequireGroupBasedAdminsEnabled: {
                event_type: "REQUIRE_GROUP_BASED_ADMINS_ENABLED";
                organization_id: string;
            };
            AuditLogEventSecretDeleted: {
                event_type: "SECRET_DELETED";
                secret_id: string;
                secret_name: string;
            };
            AuditLogEventSecretUpdated: {
                event_type: "SECRET_UPDATED";
                secret_id: string;
                secret_name: string;
            };
            AuditLogEventSshCertificateSigned: {
                event_type: "SSH_CERTIFICATE_SIGNED";
                expires_at: string;
                project_id: string;
                proxy_address: string;
                replica_id: string;
                workload_id: string;
                workload_type: string;
            };
            AuditLogEventType: | "MODEL_DEPLOYED"
            | "MODEL_DEPLOYMENT_ACTIVATED"
            | "MODEL_DEPLOYMENT_DEACTIVATED"
            | "MODEL_DEPLOYMENT_RETRIED"
            | "MODEL_DEPLOYMENT_PROMOTED"
            | "MODEL_DEPLOYMENT_AUTOSCALING_SETTINGS_CHANGED"
            | "MODEL_DEPLOYMENT_REQUEST_BACKPRESSURE_SETTINGS_CHANGED"
            | "MODEL_DEPLOYMENT_INSTANCE_TYPE_CHANGED"
            | "MODEL_DEPLOYMENT_DELETED"
            | "MODEL_DELETED"
            | "CHAIN_DEPLOYED"
            | "CHAIN_DEPLOYMENT_ACTIVATED"
            | "CHAIN_DEPLOYMENT_DEACTIVATED"
            | "CHAIN_DEPLOYMENT_PROMOTED"
            | "CHAINLET_AUTOSCALING_SETTINGS_CHANGED"
            | "CHAINLET_INSTANCE_TYPE_CHANGED"
            | "CHAIN_DEPLOYMENT_DELETED"
            | "CHAIN_DELETED"
            | "CHAIN_ENVIRONMENT_CREATED"
            | "CHAIN_ENVIRONMENT_UPDATED"
            | "SECRET_UPDATED"
            | "SECRET_DELETED"
            | "API_KEY_CREATED"
            | "API_KEY_DELETED"
            | "GATEWAY_ENDPOINT_CREATED"
            | "GATEWAY_ENDPOINT_UPDATED"
            | "GATEWAY_ENDPOINT_DELETED"
            | "USER_INVITED"
            | "USER_JOINED_ORGANIZATION"
            | "WEBHOOK_SIGNING_SECRET_CREATED"
            | "WEBHOOK_SIGNING_SECRET_ROTATED"
            | "WEBHOOK_SIGNING_SECRET_DELETED"
            | "USER_ROLE_UPDATED"
            | "USER_TEAM_ROLE_UPDATED"
            | "USER_REMOVED"
            | "DIRECTORY_GROUP_ROLE_UPDATED"
            | "REQUIRE_GROUP_BASED_ADMINS_ENABLED"
            | "ENVIRONMENT_CREATED"
            | "ENVIRONMENT_UPDATED"
            | "ENVIRONMENT_DELETED"
            | "REPLICA_TERMINATED"
            | "MODEL_PROMOTION_CONTROL_ACTION"
            | "SSH_CERTIFICATE_SIGNED"
            | "VOLUME_DELETED"
            | "VOLUME_VERSION_DELETED"
            | "VOLUME_VERSION_RESTORED";
            AuditLogEventTypeGroup: | "DEPLOYED"
            | "PROMOTED"
            | "ACTIVATED_DEACTIVATED"
            | "AUTOSCALING_SETTINGS"
            | "REQUEST_BACKPRESSURE_SETTINGS"
            | "INSTANCE_TYPE_CHANGED"
            | "ENVIRONMENT_SETTINGS"
            | "REPLICA_TERMINATED"
            | "DELETED"
            | "SECRETS"
            | "API_KEYS"
            | "GATEWAY"
            | "WEBHOOK_SIGNING_SECRETS"
            | "USER_MANAGEMENT"
            | "DIRECTORY_GROUP_MANAGEMENT"
            | "SSH";
            AuditLogEventUserInvited: {
                event_type: "USER_INVITED";
                invited_user_email: string;
                role_name: string;
            };
            AuditLogEventUserJoinedOrganization: {
                event_type: "USER_JOINED_ORGANIZATION";
                new_user_email: string;
                user_id: string;
            };
            AuditLogEventUserRemoved: {
                event_type: "USER_REMOVED";
                removed_user_email: string;
            };
            AuditLogEventUserRoleUpdated: {
                event_type: "USER_ROLE_UPDATED";
                new_role_name: string;
                user_email: string;
                user_id: string;
            };
            AuditLogEventUserTeamRoleUpdated: {
                event_type: "USER_TEAM_ROLE_UPDATED";
                new_role_name: string;
                team_id: string;
                team_name: string;
                user_email: string;
                user_id: string;
            };
            AuditLogEventVolumeDeleted: {
                event_type: "VOLUME_DELETED";
                namespace: string;
                versions_deleted: number;
                volume_name: string;
                volume_ref: string;
            };
            AuditLogEventVolumeVersionDeleted: {
                digest: string;
                event_type: "VOLUME_VERSION_DELETED";
                namespace: string;
                version: string;
                volume_name: string;
                volume_ref: string;
            };
            AuditLogEventVolumeVersionRestored: {
                digest: string;
                event_type: "VOLUME_VERSION_RESTORED";
                namespace: string;
                version: string;
                volume_name: string;
                volume_ref: string;
            };
            AuditLogEventWebhookSigningSecretCreated: {
                event_type: "WEBHOOK_SIGNING_SECRET_CREATED";
                webhook_signing_secret_id: string;
            };
            AuditLogEventWebhookSigningSecretDeleted: {
                event_type: "WEBHOOK_SIGNING_SECRET_DELETED";
                webhook_signing_secret_id: string;
            };
            AuditLogEventWebhookSigningSecretRotated: {
                event_type: "WEBHOOK_SIGNING_SECRET_ROTATED";
                webhook_signing_secret_id: string;
            };
            AuditLogPromotionControlAction: | "PAUSE"
            | "RESUME"
            | "FORCE_CANCEL"
            | "FORCE_ROLL_FORWARD"
            | "GRACEFUL_CANCEL";
            AuditLogSortDirection: "DESC"
            | "ASC";
            AuditLogSource: "UI" | "API" | "MCP" | "SYSTEM" | "OTHER";
            AuthCode: {
                auth_code: string;
                auth_url: string;
                expires_at: string | null;
                generated_at: string | null;
                replica_id: string;
                session_id: string;
                tunnel_name: string | null;
                working_directory: string | null;
            };
            AuthMethod: "CUSTOM_SECRET"
            | "AWS_OIDC"
            | "GCP_OIDC"
            | "AWS_ASSUME_ROLE";
            AutoscalingSchedule: {
                autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"];
                cadence: "DAILY" | "HOURLY";
                enabled: boolean;
                end_hour: number | null;
                end_minute: number;
                id: string;
                name: string;
                start_hour: number | null;
                start_minute: number;
                weekdays: components["schemas"]["AutoscalingScheduleWeekday"][];
            };
            AutoscalingScheduleSettings: {
                autoscaling_window: number
                | null;
                concurrency_target: number | null;
                max_replica: number;
                max_scale_down_rate: number | null;
                min_replica: number;
                scale_down_delay: number | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AutoscalingScheduleSettingsRequest: {
                autoscaling_window: number
                | null;
                concurrency_target: number | null;
                max_replica: number;
                max_scale_down_rate: number | null;
                min_replica: number;
                scale_down_delay: number | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AutoscalingScheduleState: {
                autoscaling_settings: components["schemas"]["AutoscalingSettings"];
                schedule_id: string
                | null;
            };
            AutoscalingScheduleUpsert: {
                autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"];
                cadence: "DAILY"
                | "HOURLY";
                enabled: boolean;
                end_hour?: number | null;
                end_minute: number;
                id?: string | null;
                name: string;
                start_hour?: number | null;
                start_minute: number;
                weekdays: components["schemas"]["AutoscalingScheduleWeekday"][];
            };
            AutoscalingScheduleWeekday: | "SUNDAY"
            | "MONDAY"
            | "TUESDAY"
            | "WEDNESDAY"
            | "THURSDAY"
            | "FRIDAY"
            | "SATURDAY";
            AutoscalingSettings: {
                autoscaling_window: number
                | null;
                concurrency_target: number;
                max_replica: number;
                max_scale_down_rate: number | null;
                min_replica: number;
                scale_down_delay: number | null;
                target_in_flight_tokens: number | null;
                target_utilization_percentage: number | null;
            };
            AwsAssumeRole: { baseten_role_arn: string; external_id: string };
            AwsAssumeRoleDockerAuth: { region: string; role_arn: string };
            AWSCredentials: {
                aws_access_key_id: string;
                aws_secret_access_key: string;
                aws_session_token: string;
            };
            AwsIamDockerAuth: {
                access_key_secret_ref: components["schemas"]["SecretReference"];
                secret_access_key_secret_ref: components["schemas"]["SecretReference"];
            };
            AwsOidcDockerAuth: { region: string; role_arn: string };
            BasetenLatestCheckpointConfig: {
                job_id?: string | null;
                project_name?: string | null;
                typ: "baseten_latest_checkpoint";
            };
            BasetenNamedCheckpointConfig: {
                checkpoint_name: string;
                job_id?: string
                | null;
                project_name?: string | null;
                typ: "baseten_named_checkpoint";
            };
            BenchmarkSnapshot: {
                embedding?: components["schemas"]["EmbeddingBenchmarkMetrics"]
                | null;
                llm?: components["schemas"]["LLMBenchmarkMetrics"] | null;
                measured_at: string;
                profile?: string | null;
                replicas?: number | null;
                run_id: string;
                tts?: components["schemas"]["TTSBenchmarkMetrics"] | null;
            };
            BillableResource: {
                base_model: string
                | null;
                chain_metadata: components["schemas"]["ChainMetadata"] | null;
                environment_name: string | null;
                id: string;
                instance_type: string | null;
                is_deleted: boolean;
                kind: components["schemas"]["ResourceKind"];
                model_id: string | null;
                model_name: string | null;
                name: string | null;
                team_id: string | null;
                team_name: string | null;
            };
            BucketWidth: "1m"
            | "1h"
            | "1d";
            CancelPromotionResponse: {
                message: string;
                status: components["schemas"]["CancelPromotionStatus"];
            };
            CancelPromotionStatus: "CANCELED"
            | "RAMPING_DOWN";
            CapacityAtSubmit: {
                gpu_type: string;
                last_modified: string;
                max_gpus: number;
                min_gpus: number | null;
            };
            Chain: {
                created_at: string;
                deployments_count: number;
                id: string;
                name: string;
                team_name: string;
            };
            ChainDeployment: {
                chain_id: string;
                chainlets: components["schemas"]["Chainlet"][];
                created_at: string;
                environment: string
                | null;
                id: string;
                status: components["schemas"]["DeploymentStatus"];
            };
            ChainDeployments: {
                deployments: components["schemas"]["ChainDeployment"][];
            };
            ChainDeploymentTombstone: {
                chain_id: string;
                deleted: boolean;
                id: string;
            };
            ChainEnvironment: {
                candidate_deployment: components["schemas"]["ChainDeployment"]
                | null;
                chain_id: string;
                chainlet_settings: components["schemas"]["ChainletEnvironmentSettings"][];
                created_at: string;
                current_deployment: components["schemas"]["ChainDeployment"] | null;
                name: string;
                promotion_settings: components["schemas"]["PromotionSettings"];
            };
            Chainlet: {
                active_replica_count: number;
                autoscaling_settings: components["schemas"]["AutoscalingSettings"]
                | null;
                id: string;
                instance_type_name: string;
                name: string;
                status: components["schemas"]["DeploymentStatus"];
            };
            ChainletEnvironmentAutoscalingSettingsUpdate: {
                autoscaling_settings: components["schemas"]["UpdateAutoscalingSettings"];
                chainlet_name: string;
            };
            ChainletEnvironmentInstanceTypeUpdate: {
                chainlet_name: string;
                instance_type_id: string;
            };
            ChainletEnvironmentSettings: {
                autoscaling_settings: | components["schemas"]["AutoscalingSettings"]
                | null;
                chainlet_name: string;
                instance_type: components["schemas"]["InstanceType"];
            };
            ChainletEnvironmentSettingsRequest: {
                autoscaling_settings?: | components["schemas"]["UpdateAutoscalingSettings"]
                | null;
                chainlet_name: string;
                instance_type_id?: string;
            };
            ChainMetadata: {
                chain_deployment_id: string;
                chain_id: string;
                chain_name: string
                | null;
            };
            Chains: { chains: components["schemas"]["Chain"][] };
            ChainTombstone: { deleted: boolean; id: string };
            CheckpointFile: {
                last_modified: string;
                node_rank: number;
                relative_file_name: string;
                size_bytes: number;
                url: string;
            };
            CheckpointSyncStatus: "SYNCING"
            | "COMPLETED";
            CreateApiKeyForGroupRequest: { name?: string | null };
            CreateApiKeyForGroupResponse: {
                api_key: string;
                name: string | null;
                prefix: string;
            };
            CreateAPIKeyRequest: {
                model_ids?: string[]
                | null;
                name?: string | null;
                team_id?: string | null;
                type: components["schemas"]["APIKeyCategory"];
            };
            CreateChainEnvironmentRequest: {
                chainlet_settings?: | components["schemas"]["ChainletEnvironmentSettingsRequest"][]
                | null;
                name: string;
                promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
                | null;
            };
            CreateDeploymentPatchRequest: {
                next_patch_point: components["schemas"]["DeploymentPatchPoint"];
                patch_ops: (
                    | components["schemas"]["DeploymentPatchOpModelCode"]
                    | components["schemas"]["DeploymentPatchOpPackage"]
                    | components["schemas"]["DeploymentPatchOpConfig"]
                    | components["schemas"]["DeploymentPatchOpPythonRequirement"]
                    | components["schemas"]["DeploymentPatchOpEnvVar"]
                    | components["schemas"]["DeploymentPatchOpExternalData"]
                )[];
                prev_patch_hash: string;
            };
            CreateDeploymentPatchResponse: {
                patch_point: components["schemas"]["DeploymentPatchPointWithHash"];
            };
            CreatedModelDeployment: {
                deployment: components["schemas"]["Deployment"];
                model: components["schemas"]["Model"];
            };
            CreateEndpointRequest: {
                region?: components["schemas"]["SharedEndpointRegion"];
                slug: string;
                targets: components["schemas"]["EndpointTargetRequest"][];
            };
            CreateEnvironmentRequest: {
                autoscaling_settings?: | components["schemas"]["UpdateAutoscalingSettings"]
                | null;
                name: string;
                promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
                | null;
                request_backpressure_settings?: | components["schemas"]["UpdateRequestBackpressureSettings"]
                | null;
            };
            CreateGroupHierarchy: {
                limit_enforcement?: components["schemas"]["LimitEnforcement"]
                | null;
                parent_group_id?: string | null;
            };
            CreateGroupRequest: {
                hierarchy: components["schemas"]["CreateGroupHierarchy"];
                metadata: components["schemas"]["GroupMetadata"];
                models: components["schemas"]["ModelConfig"][];
            };
            CreateJobWeightConfig: {
                allow_patterns?: string[]
                | null;
                auth?: components["schemas"]["TrainingWeightAuth"] | null;
                auth_secret_name?: string | null;
                ignore_patterns?: string[] | null;
                mount_location: string;
                source: string;
            };
            CreateLibraryListingRequest: {
                closed_source?: boolean;
                display_name: string;
                is_public?: boolean;
                user_defined_id: string;
            };
            CreateLibraryListingVersionRequest: {
                allow_truss_download?: boolean;
                closed_source?: boolean;
                display_name?: string
                | null;
                is_public?: boolean;
                oracle_version_id: string;
                version_tag: string;
            };
            CreateLLMModelRequest: {
                additional_autoscaling_config?: { [key: string]: unknown }
                | null;
                autoscaling_settings?:
                    | components["schemas"]["UpdateAutoscalingSettings"]
                    | null;
                environment_variables?: { [key: string]: unknown };
                llm_config?: { [key: string]: unknown };
                llm_version?: string | null;
                metadata?: { [key: string]: unknown } | null;
                model_metadata?: { [key: string]: unknown } | null;
                name: string;
                region?: string | null;
                resources: { [key: string]: unknown };
                weights?: { [key: string]: unknown }[] | null;
            };
            CreateLLMModelVersionRequest: {
                additional_autoscaling_config?: { [key: string]: unknown }
                | null;
                autoscaling_settings?:
                    | components["schemas"]["UpdateAutoscalingSettings"]
                    | null;
                environment_variables?: { [key: string]: unknown };
                llm_config?: { [key: string]: unknown };
                llm_version?: string | null;
                metadata?: { [key: string]: unknown } | null;
                model_metadata?: { [key: string]: unknown } | null;
                region?: string | null;
                resources: { [key: string]: unknown };
                weights?: { [key: string]: unknown }[] | null;
            };
            CreateLoopsRunRequest: {
                availability_model?: components["schemas"]["V1AvailabilityModel"];
                base_model: string;
                lora_rank?: number;
                max_seq_len?: number
                | null;
                name?: string | null;
                path?: string | null;
                replicas?: number;
                reuse_from_run_id?: string | null;
                reuse_from_session_id?: string | null;
                scale_down_delay_seconds?: number;
                seed?: number | null;
                session_id: string;
            };
            CreateLoopsRunResponse: { run: components["schemas"]["LoopsRun"] };
            CreateLoopsSamplerRequest: {
                base_model?: string | null;
                max_seq_length?: number | null;
                model_path?: string | null;
                reuse_from_session_id?: string | null;
                run_id?: string | null;
                session_id: string;
            };
            CreateLoopsSamplerResponse: {
                sampler: components["schemas"]["LoopsSampler"];
            };
            CreateLoopsSessionResponse: {
                session: components["schemas"]["LoopsSession"];
            };
            CreateModelDeploymentRequest: {
                source: components["schemas"]["DeploymentArchiveSource"];
            };
            CreateModelRequest: {
                source: | components["schemas"]["LibraryListingSource"]
                | components["schemas"]["ModelArchiveSource"];
            };
            CreateTrainingJob: {
                compute?: components["schemas"]["CreateTrainingJobCompute"];
                enable_baseten_workdir?: boolean;
                image: components["schemas"]["CreateTrainingJobImage"];
                interactive_session?: | components["schemas"]["InteractiveSessionConfig"]
                | null;
                name?: string
                | null;
                priority?: number | null;
                runtime?: components["schemas"]["CreateTrainingJobRuntime"];
                truss_user_env?: components["schemas"]["TrussUserEnv"] | null;
                weights?: components["schemas"]["CreateJobWeightConfig"][];
            };
            CreateTrainingJobAccelerator: { accelerator: string; count: number };
            CreateTrainingJobCacheConfig: {
                enable_legacy_hf_mount?: boolean;
                enabled?: boolean;
                mount_base_path?: string;
                require_cache_affinity?: boolean;
            };
            CreateTrainingJobCheckpointingConfig: {
                checkpoint_path?: string
                | null;
                enabled?: boolean;
                volume_size_gib?: number | null;
            };
            CreateTrainingJobCompute: {
                accelerator?: | components["schemas"]["CreateTrainingJobAccelerator"]
                | null;
                availability_model?: components["schemas"]["V1AvailabilityModel"];
                cpu_count?: number;
                memory?: string;
                node_count?: number;
            };
            CreateTrainingJobImage: {
                base_image: string;
                docker_auth?: components["schemas"]["DockerAuth"]
                | null;
            };
            CreateTrainingJobRequest: {
                training_job: components["schemas"]["CreateTrainingJob"];
            };
            CreateTrainingJobResponse: {
                training_job: components["schemas"]["TrainingJob"];
            };
            CreateTrainingJobRuntime: {
                artifacts?: components["schemas"]["CreateTrainingJobS3Artifact"][];
                cache_config?: | components["schemas"]["CreateTrainingJobCacheConfig"]
                | null;
                checkpointing_config?: components["schemas"]["CreateTrainingJobCheckpointingConfig"];
                enable_cache?: boolean
                | null;
                environment_variables?: { [key: string]: string | { name: string } };
                load_checkpoint_config?:
                    | components["schemas"]["LoadCheckpointConfig"]
                    | null;
                start_commands?: string[];
            };
            CreateTrainingJobS3Artifact: { s3_bucket: string; s3_key: string };
            CreateVolumeTokenRequest: {
                correlation_id?: string | null;
                namespaces: string[];
                scopes: components["schemas"]["VolumeTokenScope"][];
                volumes: string[];
            };
            CreateVolumeTokenResponse: {
                bdn_endpoint: string
                | null;
                expires_at: string;
                namespaces: string[];
                scopes: components["schemas"]["VolumeTokenScope"][];
                token: string;
                volumes: string[];
            };
            DailyDedicatedUsage: {
                compute_cost: number
                | string;
                date: string;
                inference_requests: number;
                minutes: number;
                subtotal: number | string;
                surcharge_cost: number | string;
            };
            DailyModelApiUsage: {
                cached_input_tokens: number;
                date: string;
                input_tokens: number;
                output_tokens: number;
                subtotal: number
                | string;
            };
            DailyTrainingUsage: {
                date: string;
                minutes: number;
                subtotal: number
                | string;
            };
            DeactivateLoopsDeploymentResponse: {
                base_model: string;
                id: string;
                user: components["schemas"]["User"];
            };
            DeactivateLoopsRunResponse: {
                base_model: string;
                id: string;
                user: components["schemas"]["User"];
            };
            DeactivateResponse: { no_op: boolean; success: boolean };
            DedicatedItem: {
                billable_resource: components["schemas"]["BillableResource"];
                compute_cost: number | string;
                daily?: components["schemas"]["DailyDedicatedUsage"][];
                inference_requests: number;
                minutes: number;
                subtotal: number | string;
                surcharge_cost: number | string;
            };
            DedicatedUsage: {
                breakdown?: components["schemas"]["DedicatedItem"][];
                credits_used: number
                | string;
                minutes: number;
                subtotal: number | string;
                total: number | string;
            };
            DeleteVolumeRequest: { expected_sequence?: number
            | null };
            DeleteVolumeResponse: {
                name: string;
                namespace: string;
                versions_deleted: number;
                volume_sequence: number;
            };
            DeleteVolumeVersionRequest: { expected_sequence?: number
            | null };
            DeleteVolumeVersionResponse: {
                delete_after: string;
                digest: string;
                lifecycle: string;
                namespace: string;
                version_ref: string;
                volume: string;
                volume_sequence: number;
            };
            Deployment: {
                active_replica_count: number;
                autoscaling_settings: components["schemas"]["AutoscalingSettings"]
                | null;
                created_at: string;
                environment: string | null;
                id: string;
                instance_type_name: string | null;
                is_development: boolean;
                is_production: boolean;
                labels: { [key: string]: unknown } | null;
                model_id: string;
                name: string;
                region: components["schemas"]["Region"] | null;
                request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"];
                status: components["schemas"]["DeploymentStatus"];
            };
            DeploymentArchivePayload: {
                config: { [key: string]: unknown };
                create_environment_if_missing?: boolean;
                deploy_timeout_minutes?: number | null;
                deployment_name?: string | null;
                environment_name?: string | null;
                is_development?: boolean;
                labels?: { [key: string]: unknown } | null;
                preserve_env_instance_type?: boolean;
                raw_config?: string | null;
                region?: string | null;
                user_env?: { [key: string]: unknown } | null;
            };
            DeploymentArchiveSource: {
                deployment: components["schemas"]["DeploymentArchivePayload"];
                kind: "model_archive";
                s3_key?: string
                | null;
            };
            DeploymentConfigOutputFormat: "raw"
            | "parsed"
            | "both";
            DeploymentConfigResponse: {
                config: { [key: string]: unknown } | null;
                raw_config: string | null;
            };
            DeploymentPatchAction: "ADD"
            | "UPDATE"
            | "REMOVE";
            DeploymentPatchOpConfig: {
                config: { [key: string]: unknown };
                path?: string;
                type: "config";
            };
            DeploymentPatchOpEnvVar: {
                action: components["schemas"]["DeploymentPatchAction"];
                name: string;
                type: "environment_variable";
                value?: string
                | null;
            };
            DeploymentPatchOpExternalData: {
                action: components["schemas"]["DeploymentPatchAction"];
                item: { [key: string]: string };
                type: "external_data";
            };
            DeploymentPatchOpModelCode: {
                action: components["schemas"]["DeploymentPatchAction"];
                content?: string
                | null;
                content_bytes?: string | null;
                hot_reload?: boolean;
                path: string;
                type: "model_code";
            };
            DeploymentPatchOpPackage: {
                action: components["schemas"]["DeploymentPatchAction"];
                content?: string
                | null;
                content_bytes?: string | null;
                path: string;
                type: "package";
            };
            DeploymentPatchOpPythonRequirement: {
                action: components["schemas"]["DeploymentPatchAction"];
                requirement: string;
                type: "python_requirement";
            };
            DeploymentPatchPoint: {
                config: string;
                content_hashes: { [key: string]: string
                | null };
                requirements?: string[];
            };
            DeploymentPatchPointWithHash: {
                config: string;
                content_hashes: { [key: string]: string
                | null };
                hash: string;
                requirements?: string[];
            };
            Deployments: { deployments: components["schemas"]["Deployment"][] };
            DeploymentStatus:
                | "BUILDING"
                | "DEPLOYING"
                | "DEPLOY_FAILED"
                | "LOADING_MODEL"
                | "ACTIVE"
                | "UNHEALTHY"
                | "BUILD_FAILED"
                | "BUILD_STOPPED"
                | "DEACTIVATING"
                | "INACTIVE"
                | "FAILED"
                | "UPDATING"
                | "SCALED_TO_ZERO"
                | "WAKING_UP";
            DeploymentTombstone: { deleted: boolean; id: string; model_id: string };
            DockerAuth: {
                auth_method: components["schemas"]["DockerAuthType"];
                aws_assume_role_docker_auth?:
                    | components["schemas"]["AwsAssumeRoleDockerAuth"]
                    | null;
                aws_iam_docker_auth?: components["schemas"]["AwsIamDockerAuth"]
                | null;
                aws_oidc_docker_auth?: components["schemas"]["AwsOidcDockerAuth"] | null;
                gcp_oidc_docker_auth?: components["schemas"]["GcpOidcDockerAuth"] | null;
                gcp_service_account_json_docker_auth?:
                    | components["schemas"]["GcpServiceAccountJsonDockerAuth"]
                    | null;
                registry: string;
                registry_secret_docker_auth?: | components["schemas"]["RegistrySecretDockerAuth"]
                | null;
            };
            DockerAuthType: | "GCP_SERVICE_ACCOUNT_JSON"
            | "AWS_IAM"
            | "AWS_OIDC"
            | "GCP_OIDC"
            | "REGISTRY_SECRET"
            | "AWS_ASSUME_ROLE";
            DownloadDeploymentResponse: { download_url: string };
            DownloadTrainingJobResponse: { artifact_presigned_urls: string[] };
            EffectiveModelConfig: {
                rate_limits?: components["schemas"]["EffectiveRateLimit"][];
                slug: string;
                usage_limits?: components["schemas"]["EffectiveUsageLimit"][];
            };
            EffectiveRateLimit: {
                source_group: string;
                threshold: number;
                type: components["schemas"]["LimitType"];
                unit: components["schemas"]["RateLimitUnit"];
            };
            EffectiveUsageLimit: {
                source_group: string;
                threshold: number;
                type: components["schemas"]["LimitType"];
                unit: components["schemas"]["UsageLimitUnit"];
            };
            EmbeddingBenchmarkMetrics: {
                e2e_latency_ms_p50?: number
                | null;
                e2e_latency_ms_p99?: number | null;
                input_tokens_per_sec?: number | null;
                requests_per_sec?: number | null;
            };
            Endpoint: {
                created_at: string;
                id: string;
                region: components["schemas"]["SharedEndpointRegion"];
                slug: string;
                targets: components["schemas"]["EndpointTarget"][];
                updated_at: string;
            };
            EndpointsResponse: {
                items: components["schemas"]["Endpoint"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            EndpointTarget: {
                base_url: string
                | null;
                environment_name: string | null;
                model_id: string | null;
                provider: components["schemas"]["GatewayProvider"];
                secret_id: string | null;
                target_model: string | null;
                vertex_config: components["schemas"]["VertexTargetConfig"] | null;
            };
            EndpointTargetRequest: {
                base_url?: string
                | null;
                environment_name?: string | null;
                model_id?: string | null;
                provider: components["schemas"]["GatewayProvider"];
                secret_id?: string | null;
                target_model?: string | null;
                vertex_config?: components["schemas"]["VertexTargetConfig"] | null;
            };
            EndpointTombstone: { id: string; slug: string };
            Environment: {
                autoscaling_schedules:
                    | components["schemas"]["EnvironmentAutoscalingSchedules"]
                    | null;
                autoscaling_settings: components["schemas"]["AutoscalingSettings"];
                candidate_deployment: components["schemas"]["Deployment"]
                | null;
                created_at: string;
                current_deployment: components["schemas"]["Deployment"] | null;
                in_progress_promotion:
                    | components["schemas"]["InProgressPromotion"]
                    | null;
                instance_type: components["schemas"]["InstanceType"];
                model_id: string;
                name: string;
                promotion_settings: components["schemas"]["PromotionSettings"];
                request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"];
            };
            EnvironmentAutoscalingSchedules: {
                applied_state: | components["schemas"]["AutoscalingScheduleState"]
                | null;
                schedules: (
                    | components["schemas"]["AutoscalingSchedule"]
                    | components["schemas"]["OneTimeAutoscalingSchedule"]
                )[];
                timezone: string
                | null;
            };
            EnvironmentGroup: {
                manage_access: components["schemas"]["EnvironmentGroupManageAccess"];
                name: string;
                team_id: string;
                team_name: string;
            };
            EnvironmentGroupManageAccess: {
                is_restricted: boolean;
                users?: components["schemas"]["EnvironmentGroupUser"][];
            };
            EnvironmentGroups: {
                items: components["schemas"]["EnvironmentGroup"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            EnvironmentGroupUser: {
                email: string
                | null;
                name: string | null;
                user_id: string;
            };
            Environments: { environments: components["schemas"]["Environment"][] };
            EnvironmentTombstone: { deleted: boolean; model_id: string; name: string };
            FileSummary: {
                file_type: string;
                modified: string;
                path: string;
                permissions: string;
                size_bytes: number;
            };
            GatewayEvent: {
                apiKeyPrefix: string;
                externalEntityId: string;
                idempotencyKey: string;
                modelSlug: string;
                requestId: string;
                timestamp: string;
                tokens: components["schemas"]["GatewayEventTokens"];
                type: string;
            };
            GatewayEventsResponse: {
                items: components["schemas"]["GatewayEvent"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            GatewayEventTokens: {
                cachedInputTokens: number;
                inputTokens: number;
                outputTokens: number;
            };
            GatewayKeyInfo: { name: string
            | null; prefix: string };
            GatewayProvider:
                | "ANTHROPIC"
                | "OPENAI"
                | "XAI"
                | "BASETEN"
                | "BASETEN_MODEL_API"
                | "VERTEX"
                | "OPENAI_COMPATIBLE";
            GcpOidcDockerAuth: {
                service_account: string;
                workload_identity_provider: string;
            };
            GcpServiceAccountJsonDockerAuth: {
                service_account_json_secret_ref: components["schemas"]["SecretReference"];
            };
            GetAuditLogsRequest: {
                chain_deployment_ids?: string[];
                cursor?: string
                | null;
                deployment_ids?: string[];
                direction?: components["schemas"]["AuditLogSortDirection"];
                end_epoch_millis?: number | null;
                environment_names?: string[];
                event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
                limit?: number;
                search?: string | null;
                sources?: components["schemas"]["AuditLogSource"][];
                start_epoch_millis?: number | null;
                user_ids?: string[];
            };
            GetAuthCodesResponse: { auth_codes: components["schemas"]["AuthCode"][] };
            GetBillingModelApisRequest: {
                api_key_prefixes?: string[];
                cursor?: string | null;
                end_date?: string | null;
                group_by?: components["schemas"]["ModelApiCostDimension"][];
                limit?: number;
                models?: string[];
                service_tiers?: string[];
                start_date?: string | null;
                user_ids?: string[];
            };
            GetBillingUsageSummaryRequest: { end_date: string; start_date: string };
            GetBlobCredentialsResponse: {
                creds: components["schemas"]["AWSCredentials"];
                s3_bucket: string;
                s3_key: string;
            };
            GetCacheSummaryResponse: {
                file_summaries: components["schemas"]["FileSummary"][];
                project_id: string;
                timestamp: string;
            };
            GetChainsAuditLogsRequest: {
                chain_deployment_ids?: string[];
                cursor?: string
                | null;
                deployment_ids?: string[];
                direction?: components["schemas"]["AuditLogSortDirection"];
                end_epoch_millis?: number | null;
                environment_names?: string[];
                event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
                limit?: number;
                search?: string | null;
                sources?: components["schemas"]["AuditLogSource"][];
                start_epoch_millis?: number | null;
                user_ids?: string[];
            };
            GetChainsDeploymentsChainletsLogsRequest: {
                component?: string
                | null;
                direction?: components["schemas"]["SortOrder"] | null;
                end_epoch_millis?: number | null;
                excludes?: string[];
                includes?: string[];
                limit?: number | null;
                min_level?: components["schemas"]["LogLevel"] | null;
                replica?: string | null;
                request_id?: string | null;
                search_pattern?: string | null;
                start_epoch_millis?: number | null;
            };
            GetDeploymentLogsRequest: {
                component?: string
                | null;
                direction?: components["schemas"]["SortOrder"] | null;
                end_epoch_millis?: number | null;
                excludes?: string[];
                includes?: string[];
                limit?: number | null;
                min_level?: components["schemas"]["LogLevel"] | null;
                replica?: string | null;
                request_id?: string | null;
                search_pattern?: string | null;
                start_epoch_millis?: number | null;
            };
            GetDeploymentPatchesStateResponse: {
                pending_patch_point: | components["schemas"]["DeploymentPatchPointWithHash"]
                | null;
                running_patch_point: components["schemas"]["DeploymentPatchPointWithHash"];
            };
            GetGatewayEventsRequest: {
                api_keys?: string[];
                cursor?: string
                | null;
                end_time?: string | null;
                external_entity_ids?: string[];
                limit?: number | null;
                start_time?: string | null;
            };
            GetLogsResponse: { logs: components["schemas"]["Log"][] };
            GetLoopsCapabilitiesResponse: {
                supported_models: components["schemas"]["SupportedModel"][];
            };
            GetLoopsCheckpointsFilesRequest: {
                page_size?: number;
                page_token?: number;
            };
            GetLoopsCheckpointsRequest: {
                base_model?: string
                | null;
                checkpoint_path?: string | null;
                run_id?: string | null;
            };
            GetLoopsDeploymentMetricsRequest: {
                end_epoch_millis?: number
                | null;
                start_epoch_millis?: number | null;
                step_seconds?: number | null;
                time_divisor_seconds?: number | null;
            };
            GetLoopsDeploymentMetricsResponse: {
                deployment_id: string;
                metrics: components["schemas"]["LoopsDeploymentMetrics"];
            };
            GetLoopsDeploymentResponse: {
                deployment: components["schemas"]["LoopsDeployment"];
            };
            GetLoopsDeploymentsDebugArchiveFilesRequest: {
                page_size?: number;
                page_token?: string
                | null;
            };
            GetLoopsDeploymentsLogsRequest: {
                direction?: components["schemas"]["SortOrder"]
                | null;
                end_epoch_millis?: number | null;
                limit?: number | null;
                min_level?: components["schemas"]["LogLevel"] | null;
                start_epoch_millis?: number | null;
            };
            GetLoopsDeploymentsRequest: { scope?: string
            | null };
            GetLoopsRunResponse: { run: components["schemas"]["LoopsRun"] };
            GetLoopsRunsRequest: {
                base_model?: string | null;
                run_id?: string | null;
                scope?: string | null;
            };
            GetLoopsSamplerResponse: {
                sampler: components["schemas"]["LoopsSampler"];
            };
            GetLoopsSamplersRequest: { scope?: string
            | null };
            GetLoopsSessionResponse: {
                session: components["schemas"]["LoopsSession"];
            };
            GetLoopsUserConfigResponse: {
                user_config: components["schemas"]["LoopsUserConfig"];
            };
            GetModelApisRequest: {
                added_only?: boolean;
                cursor?: string
                | null;
                limit?: number;
            };
            GetModelApisUsageRequest: {
                api_keys?: string[];
                bucket_width?: components["schemas"]["BucketWidth"];
                cursor?: string
                | null;
                end_time?: string | null;
                group_by?: components["schemas"]["UsageDimension"][];
                limit?: number | null;
                models?: string[];
                start_time?: string | null;
                user_ids?: string[];
            };
            GetModelMetricsResponse: {
                end_epoch_millis: number;
                metric_descriptors: components["schemas"]["ModelMetricDescriptor"][];
                metric_values: components["schemas"]["ModelMetricValueSet"][];
                mode: components["schemas"]["ModelMetricMode"];
                start_epoch_millis: number;
                step_seconds: number
                | null;
            };
            GetModelsAuditLogsRequest: {
                chain_deployment_ids?: string[];
                cursor?: string
                | null;
                deployment_ids?: string[];
                direction?: components["schemas"]["AuditLogSortDirection"];
                end_epoch_millis?: number | null;
                environment_names?: string[];
                event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
                limit?: number;
                search?: string | null;
                sources?: components["schemas"]["AuditLogSource"][];
                start_epoch_millis?: number | null;
                user_ids?: string[];
            };
            GetModelsDeploymentsConfigRequest: {
                output_format?: components["schemas"]["DeploymentConfigOutputFormat"];
            };
            GetModelsDeploymentsLogsRequest: {
                component?: string
                | null;
                direction?: components["schemas"]["SortOrder"] | null;
                end_epoch_millis?: number | null;
                excludes?: string[];
                includes?: string[];
                limit?: number | null;
                min_level?: components["schemas"]["LogLevel"] | null;
                replica?: string | null;
                request_id?: string | null;
                search_pattern?: string | null;
                start_epoch_millis?: number | null;
            };
            GetModelsDeploymentsMetricsRequest: {
                end_epoch_millis?: number
                | null;
                metrics?: string[];
                mode?: components["schemas"]["ModelMetricMode"];
                start_epoch_millis?: number | null;
            };
            GetModelsDeploymentsRequest: { name?: string
            | null };
            GetModelsEnvironmentsLogsRequest: {
                component?: string | null;
                direction?: components["schemas"]["SortOrder"] | null;
                end_epoch_millis?: number | null;
                excludes?: string[];
                includes?: string[];
                limit?: number | null;
                min_level?: components["schemas"]["LogLevel"] | null;
                replica?: string | null;
                request_id?: string | null;
                search_pattern?: string | null;
                start_epoch_millis?: number | null;
            };
            GetModelsEnvironmentsMetricsRequest: {
                end_epoch_millis?: number
                | null;
                metrics?: string[];
                mode?: components["schemas"]["ModelMetricMode"];
                start_epoch_millis?: number | null;
            };
            GetModelsRequest: { name?: string
            | null };
            GetTeamsLoopsRunsRequest: {
                base_model?: string | null;
                run_id?: string | null;
                scope?: string | null;
            };
            GetTeamsLoopsSamplersRequest: { scope?: string
            | null };
            GetTeamsModelsRequest: { name?: string | null };
            GetTeamsRequest: { name?: string | null };
            GetTrainingGpuCapacityResponse: {
                gpu_capacities: components["schemas"]["TrainingGpuCapacityItem"][];
                team_gpu_capacities?: components["schemas"]["TeamTrainingGpuCapacityItem"][];
            };
            GetTrainingJobCheckpointFilesResponse: {
                next_page_token: number
                | null;
                presigned_urls: components["schemas"]["CheckpointFile"][];
                total_count: number;
            };
            GetTrainingJobCheckpointsResponse: {
                checkpoints: components["schemas"]["TrainingJobCheckpoint"][];
                training_job: components["schemas"]["TrainingJob"];
            };
            GetTrainingJobLogsRequest: {
                direction?: components["schemas"]["SortOrder"]
                | null;
                end_epoch_millis?: number | null;
                limit?: number | null;
                min_level?: components["schemas"]["LogLevel"] | null;
                start_epoch_millis?: number | null;
            };
            GetTrainingJobMetricsRequest: {
                end_epoch_millis?: number
                | null;
                start_epoch_millis?: number | null;
                step_seconds?: number | null;
            };
            GetTrainingJobMetricsResponse: {
                cache: components["schemas"]["StorageMetrics"]
                | null;
                cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
                cpu_usage: components["schemas"]["TrainingJobMetric"][];
                ephemeral_storage: components["schemas"]["StorageMetrics"];
                gpu_memory_usage_bytes: {
                    [key: string]: { timestamp: string; value: number }[];
                };
                gpu_utilization: {
                    [key: string]: { timestamp: string; value: number }[];
                };
                per_node_metrics: components["schemas"]["TrainingJobNodeMetrics"][];
                training_job: components["schemas"]["TrainingJob"];
            };
            GetTrainingJobQueueContextResponse: {
                active_at_submit: components["schemas"]["ActiveJobAtSubmit"][];
                events: components["schemas"]["QueueEvent"][];
                events_window_end: string;
                gpu_type: string;
                org_capacity: components["schemas"]["CapacityAtSubmit"]
                | null;
                pending_ahead_at_submit: components["schemas"]["PendingJobAheadAtSubmit"][];
                pending_seconds: number | null;
                released_at: string | null;
                requested_gpus: number;
                submitted_at: string;
                target_job_id: string;
                target_job_name: string | null;
                team_capacity: components["schemas"]["CapacityAtSubmit"] | null;
            };
            GetTrainingJobResponse: {
                training_job: components["schemas"]["TrainingJob"];
                training_project: components["schemas"]["TrainingProject"];
            };
            GetTrainingProjectResponse: {
                training_project: components["schemas"]["TrainingProject"];
            };
            GetTrainingProjectsJobsCheckpointFilesRequest: {
                page_size?: number;
                page_token?: number;
            };
            GetTrainingProjectsJobsLogsRequest: {
                direction?: components["schemas"]["SortOrder"]
                | null;
                end_epoch_millis?: number | null;
                limit?: number | null;
                min_level?: components["schemas"]["LogLevel"] | null;
                start_epoch_millis?: number | null;
            };
            GetTrainingProjectsJobsMetricsRequest: {
                end_epoch_millis?: number
                | null;
                start_epoch_millis?: number | null;
                step_seconds?: number | null;
            };
            GetUsersRequest: {
                cursor?: string
                | null;
                email?: string | null;
                limit?: number;
            };
            GetVolumesNamespacesRequest: { cursor?: string
            | null; limit?: number };
            GetVolumesRequest: {
                cursor?: string | null;
                limit?: number;
                namespace: string;
            };
            GetVolumesVersionsRequest: { include_tombstoned?: boolean };
            GitInfo: {
                commits_since_tag: number | null;
                has_uncommitted_changes: boolean;
                latest_commit_sha: string;
                latest_tag: string | null;
            };
            Group: {
                created_at: string;
                effective_models?: components["schemas"]["EffectiveModelConfig"][];
                hierarchy: components["schemas"]["GroupHierarchy"];
                id: string;
                metadata: components["schemas"]["GroupMetadata"];
                models?: components["schemas"]["ModelConfig"][];
            };
            GroupHierarchy: {
                limit_enforcement: components["schemas"]["LimitEnforcement"];
                parent_group_id: string
                | null;
            };
            GroupMetadata: { external_entity_id: string; name?: string
            | null };
            GroupsResponse: {
                items: components["schemas"]["Group"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            InferenceVolumeByStatusDatapoint: {
                status_2xx: number;
                status_4xx: number;
                status_5xx: number;
                timestamp: string;
            };
            InProgressPromotion: {
                error_message: string
                | null;
                percent_traffic_to_new_version: number;
                rolling_deploy: boolean | null;
                status: components["schemas"]["InProgressPromotionStatus"];
            };
            InProgressPromotionStatus: | "RELEASING"
            | "RAMPING_UP"
            | "RAMPING_DOWN"
            | "PAUSED"
            | "SUCCEEDED"
            | "FAILED"
            | "CANCELED";
            InstanceType: {
                gpu_count: number;
                gpu_memory_limit_mib: number
                | null;
                gpu_type: string | null;
                id: string;
                memory_limit_mib: number;
                millicpu_limit: number;
                name: string;
            };
            InstanceTypePrices: {
                instance_types: components["schemas"]["InstanceTypeWithPrice"][];
            };
            InstanceTypes: { instance_types: components["schemas"]["InstanceType"][] };
            InstanceTypeWithPrice: {
                instance_type: components["schemas"]["InstanceType"];
                price: number;
            };
            InteractiveSession: {
                auth_code: string
                | null;
                auth_code_generated_at: string | null;
                auth_provider: string;
                auth_url: string | null;
                authenticated_at: string | null;
                expires_at: string | null;
                id: string;
                pod_name: string;
                session_provider: string;
                timeout_minutes: number;
                trigger: string;
                tunnel_name: string | null;
                working_directory: string | null;
            };
            InteractiveSessionConfig: {
                auth_provider?: components["schemas"]["V1InteractiveSessionAuthProvider"];
                session_provider?: components["schemas"]["V1InteractiveSessionProvider"];
                timeout_minutes?: number;
                trigger?: components["schemas"]["V1InteractiveSessionTrigger"];
            };
            KeysForGroupResponse: {
                items: components["schemas"]["GatewayKeyInfo"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            LibraryListing: {
                closed_source: boolean;
                created_at: string;
                display_name: string;
                is_public: boolean;
                metadata: components["schemas"]["LibraryListingMetadata"]
                | null;
                modified_at: string;
                trending: boolean | null;
                user_defined_id: string;
            };
            LibraryListingMetadata: {
                context_length?: number
                | null;
                description?: string | null;
                input_modalities?: components["schemas"]["LibraryListingModality"][];
                license: string;
                model_api_slug?: string | null;
                output_modalities?: components["schemas"]["LibraryListingModality"][];
                parameter_count?: number | null;
                publisher?: string | null;
                release_date?: string | null;
                trending?: boolean;
                variant?: string | null;
            };
            LibraryListingModality: | "text"
            | "image"
            | "audio"
            | "video"
            | "embedding"
            | "rerank";
            LibraryListings: { listings: components["schemas"]["LibraryListing"][] };
            LibraryListingSource: {
                deployed_model_name?: string | null;
                kind: "library_listing";
                lab_display_name: string;
                user_defined_listing_id: string;
            };
            LibraryListingTombstone: { deleted: boolean; user_defined_id: string };
            LibraryListingVersion: {
                allow_truss_download: boolean;
                benchmark: components["schemas"]["BenchmarkSnapshot"] | null;
                created_at: string;
                is_live: boolean;
                modified_at: string;
                oracle_version_id: string;
                version_tag: string;
            };
            LibraryListingVersions: {
                versions: components["schemas"]["LibraryListingVersion"][];
            };
            LibraryListingVersionTombstone: { deleted: boolean; version_tag: string };
            LimitEnforcement: "CASCADING" | "INDEPENDENT";
            LimitType:
                | "REQUEST"
                | "TOKEN"
                | "CONCURRENT_REQUEST"
                | "UNCACHED_INPUT_TOKEN"
                | "OUTPUT_TOKEN";
            ListAuditLogsResponse: {
                items: components["schemas"]["AuditLogEntry"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            ListLoopsCheckpointsResponse: {
                checkpoints: components["schemas"]["LoopsCheckpoint"][];
            };
            ListLoopsDeploymentsResponse: {
                deployments: components["schemas"]["LoopsDeployment"][];
            };
            ListLoopsRunsResponse: { runs: components["schemas"]["LoopsRun"][] };
            ListLoopsSamplersResponse: {
                samplers: components["schemas"]["LoopsSampler"][];
            };
            ListTrainingJobsResponse: {
                training_jobs: components["schemas"]["TrainingJob"][];
                training_project: components["schemas"]["TrainingProject"];
            };
            ListTrainingProjectsResponse: {
                training_projects: components["schemas"]["TrainingProject"][];
            };
            ListVolumeNamespacesResponse: {
                items: string[];
                pagination: components["schemas"]["PaginationResponse"];
            };
            ListVolumesResponse: {
                items: components["schemas"]["Volume"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            ListVolumeVersionsResponse: {
                versions: components["schemas"]["VolumeVersion"][];
                volume_sequence: number;
            };
            LLMBenchmarkMetrics: {
                cost_per_1m_tokens_usd?: number
                | null;
                max_concurrent_users_at_50ms_tpot?: number | null;
                output_tokens_per_sec_per_user_p50?: number | null;
                requests_per_sec_p50?: number | null;
                ttft_ms_p50?: number | null;
            };
            LLMModelHandle: {
                hostname: string;
                instance_type_name: string
                | null;
                model_id: string;
                version_id: string;
            };
            LoadCheckpointConfig: {
                checkpoints?: (
                    | components["schemas"]["BasetenLatestCheckpointConfig"]
                    | components["schemas"]["BasetenNamedCheckpointConfig"]
                    | components["schemas"]["LoopsCheckpointConfig"]
                )[];
                download_folder?: string;
                enabled?: boolean;
            };
            Log: {
                level: components["schemas"]["LogLevel"]
                | null;
                message: string;
                replica: string | null;
                request_id: string | null;
                timestamp: string;
            };
            LogLevel: "DEBUG"
            | "INFO"
            | "WARNING"
            | "ERROR";
            LoopsCheckpoint: {
                base_model: string | null;
                checkpoint_id: string;
                checkpoint_type: string;
                created_at: string;
                id: string;
                lora_adapter_config: { [key: string]: unknown } | null;
                run_id: string;
                size_bytes: number;
                sync_status: string | null;
                target: components["schemas"]["TrainerCheckpointTarget"];
            };
            LoopsCheckpointConfig: {
                checkpoint_name: string;
                run_id: string;
                target?: "trainer"
                | "sampler";
                typ: "loops_checkpoint";
            };
            LoopsCheckpointFilesResponse: {
                next_page_token: number
                | null;
                presigned_urls: components["schemas"]["CheckpointFile"][];
                total_count: number;
            };
            LoopsDebugArchiveFilesResponse: {
                next_page_token: string
                | null;
                presigned_urls: components["schemas"]["CheckpointFile"][];
            };
            LoopsDeployment: {
                active_run_id: string
                | null;
                availability_model: components["schemas"]["V1AvailabilityModel"];
                base_model: string;
                base_url: string;
                created_at: string;
                id: string;
                instance_type: components["schemas"]["InstanceType"];
                latest_run_id: string | null;
                node_count: number;
                sampler: components["schemas"]["LoopsSampler"] | null;
                status: components["schemas"]["LoopsDeploymentStatus"];
                user: components["schemas"]["User"];
            };
            LoopsDeploymentMetrics: {
                concurrent_requests: components["schemas"]["TrainingJobMetric"][];
                cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
                cpu_usage: components["schemas"]["TrainingJobMetric"][];
                ephemeral_storage: components["schemas"]["StorageMetrics"];
                gpu_memory_usage_bytes: {
                    [key: string]: { timestamp: string; value: number }[];
                };
                gpu_utilization: {
                    [key: string]: { timestamp: string; value: number }[];
                };
                inference_volume: components["schemas"]["TrainingJobMetric"][];
                inference_volume_by_status: components["schemas"]["InferenceVolumeByStatusDatapoint"][];
                per_node_metrics: components["schemas"]["LoopsDeploymentNodeMetrics"][];
                response_time_stats: components["schemas"]["ResponseTimeDatapoint"][];
            };
            LoopsDeploymentNodeMetrics: {
                cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
                cpu_usage: components["schemas"]["TrainingJobMetric"][];
                ephemeral_storage: components["schemas"]["StorageMetrics"];
                gpu_memory_usage_bytes: {
                    [key: string]: { timestamp: string; value: number }[];
                };
                gpu_utilization: {
                    [key: string]: { timestamp: string; value: number }[];
                };
                node_id: string;
            };
            LoopsDeploymentStatus: { name: components["schemas"]["Name"] };
            LoopsRun: {
                base_model: string;
                base_url: string;
                created_at: string;
                deployment_id: string | null;
                id: string;
                name: string;
                sampler: components["schemas"]["LoopsSampler"] | null;
                session_id: string;
                status: components["schemas"]["LoopsRunStatus"];
                user: components["schemas"]["User"];
            };
            LoopsRunStatus: { name: components["schemas"]["LoopsRunStatusName"] };
            LoopsRunStatusName: "ACTIVE" | "INACTIVE";
            LoopsSampler: {
                base_model: string;
                base_url: string;
                created_at: string;
                deployment_id: string;
                id: string;
                instance_type: components["schemas"]["InstanceType"] | null;
                model_id: string;
                node_count: number;
                status: components["schemas"]["LoopsSamplerStatus"];
                user: components["schemas"]["User"];
            };
            LoopsSamplerStatus: { name: components["schemas"]["DeploymentStatus"] };
            LoopsSession: { id: string };
            LoopsUserConfig: {
                sampler_accelerator_priority: string[] | null;
                trainer_accelerator_priority: string[] | null;
            };
            Model: {
                created_at: string;
                deployments_count: number;
                development_deployment_id: string
                | null;
                id: string;
                instance_type_name: string;
                name: string;
                production_deployment_id: string | null;
                team_name: string;
            };
            ModelAPI: {
                context_length: number;
                cost_per_million_input_tokens: number
                | string
                | null;
                cost_per_million_output_tokens: number | string | null;
                description: string;
                display_name: string;
                invoke_url: string;
                model_family: string | null;
                name: string;
                org_details: components["schemas"]["ModelAPIOrgDetails"] | null;
                rate_limits: components["schemas"]["RateLimit"][];
                release_date: string;
            };
            ModelApiCostDimension: | "api_key_prefix"
            | "user"
            | "model"
            | "service_tier";
            ModelApiItem: {
                cached_input_tokens: number;
                daily?: components["schemas"]["DailyModelApiUsage"][];
                input_tokens: number;
                model_family: string
                | null;
                model_name: string;
                output_tokens: number;
                subtotal: number | string;
            };
            ModelAPIOrgDetails: { added_at: string; last_used_at: string
            | null };
            ModelApisCostBucket: {
                date: string;
                results?: components["schemas"]["ModelApisCostResult"][];
            };
            ModelApisCostResult: {
                api_key_prefixes: string[]
                | null;
                model: string | null;
                service_tier: string | null;
                subtotal: string;
                user_id: string | null;
            };
            ModelApisCostsResponse: {
                items: components["schemas"]["ModelApisCostBucket"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            ModelAPIsResponse: {
                items: components["schemas"]["ModelAPI"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            ModelApisUsage: {
                breakdown?: components["schemas"]["ModelApiItem"][];
                credits_used: number
                | string;
                subtotal: number | string;
                total: number | string;
            };
            ModelApisUsageBucket: {
                end_time: string;
                results?: components["schemas"]["ModelApisUsageResult"][];
                start_time: string;
            };
            ModelApisUsageResponse: {
                items: components["schemas"]["ModelApisUsageBucket"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            ModelApisUsageResult: {
                api_key_prefix: string
                | null;
                cached_input_tokens: number;
                input_tokens: number;
                model: string | null;
                output_tokens: number;
                request_count: number;
                uncached_input_tokens: number;
                user_id: string | null;
            };
            ModelArchiveSource: {
                deployment: components["schemas"]["DeploymentArchivePayload"];
                disable_archive_download?: boolean;
                kind: "model_archive";
                name: string;
                s3_key?: string
                | null;
            };
            ModelConfig: {
                rate_limits?: components["schemas"]["RateLimit"][];
                slug: string;
                usage_limits?: components["schemas"]["UsageLimit"][];
            };
            ModelMetricDescriptor: {
                kind: components["schemas"]["ModelMetricKind"];
                label_sets: { [key: string]: string }[];
                name: string;
                unit_hint: components["schemas"]["ModelMetricUnitHint"];
            };
            ModelMetricKind: "GAUGE"
            | "COUNTER"
            | "HISTOGRAM";
            ModelMetricMode: "CURRENT" | "SUMMARY" | "SERIES";
            ModelMetricUnitHint:
                | "PER_SECOND"
                | "SECONDS"
                | "BYTES"
                | "MEBIBYTES"
                | "COUNT"
                | "RATIO";
            ModelMetricValueSet: {
                start_epoch_millis: number;
                values: (number | null)[][];
            };
            Models: { models: components["schemas"]["Model"][] };
            ModelTombstone: { deleted: boolean; id: string };
            Name:
                | "CREATED"
                | "DEPLOYING"
                | "RUNNING"
                | "SCALED_TO_ZERO"
                | "FAILED"
                | "STOPPED"
                | "PREEMPTED";
            OneTimeAutoscalingSchedule: {
                autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"];
                cadence: "ONE_TIME";
                enabled: boolean;
                end_at: string;
                id: string;
                name: string;
                start_at: string;
            };
            OneTimeAutoscalingScheduleUpsert: {
                autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"];
                cadence: "ONE_TIME";
                enabled: boolean;
                end_at: string;
                id?: string
                | null;
                name: string;
                start_at: string;
            };
            OrderBy: { field: string; order: string };
            OrganizationInfo: {
                aws_assume_role: components["schemas"]["AwsAssumeRole"] | null;
                created_at: string;
                name: string | null;
                org_id: string;
            };
            PaginationResponse: { cursor: string
            | null; has_more: boolean };
            PatchInteractiveSessionRequest: {
                timeout_minutes?: number | null;
                trigger?: components["schemas"]["V1InteractiveSessionTrigger"] | null;
            };
            PatchInteractiveSessionResponse: {
                interactive_session: components["schemas"]["InteractiveSession"];
                message: string;
            };
            PatchLoopsUserConfigRequest: {
                sampler_accelerator_priority?: string[]
                | null;
                trainer_accelerator_priority?: string[] | null;
            };
            PatchLoopsUserConfigResponse: {
                user_config: components["schemas"]["LoopsUserConfig"];
            };
            PatchTeamTrainingGpuCapacityRequest: {
                gpu_type: string;
                max_gpus: number;
                team_id: string;
            };
            PatchTeamTrainingGpuCapacityResponse: {
                team_gpu_capacity: components["schemas"]["TeamTrainingGpuCapacityItem"];
            };
            PendingJobAheadAtSubmit: {
                instance_type_name: string;
                priority: number;
                requested_gpus: number;
                submitted_at: string;
                training_job_id: string;
                training_job_name: string
                | null;
            };
            PrepareModelUploadRequest: {
                deployment: components["schemas"]["DeploymentArchivePayload"];
                dry_run?: boolean;
                model_id?: string
                | null;
                name?: string | null;
                team_id?: string | null;
            };
            PrepareModelUploadResponse: {
                creds: components["schemas"]["AWSCredentials"]
                | null;
                s3_bucket: string | null;
                s3_key: string | null;
                s3_region: string | null;
            };
            PromoteRequest: {
                preserve_env_instance_type?: boolean;
                scale_down_previous_production?: boolean;
            };
            PromoteToChainEnvironmentRequest: {
                deployment_id: string;
                scale_down_previous_deployment?: boolean;
            };
            PromoteToEnvironmentRequest: {
                deployment_id: string;
                preserve_env_instance_type?: boolean;
                scale_down_previous_deployment?: boolean;
            };
            PromotionCleanupStrategy: "KEEP"
            | "SCALE_TO_ZERO"
            | "DEACTIVATE";
            PromotionSettings: {
                promotion_cleanup_strategy:
                    | components["schemas"]["PromotionCleanupStrategy"]
                    | null;
                ramp_up_duration_seconds: number
                | null;
                ramp_up_while_promoting: boolean | null;
                redeploy_on_promotion: boolean | null;
                rolling_deploy: boolean | null;
                rolling_deploy_config:
                    | components["schemas"]["RollingDeployConfig"]
                    | null;
            };
            QueueEvent: {
                created: string;
                event_message: string
                | null;
                exit_code: number | null;
                status: string;
                training_job_id: string;
                training_job_name: string | null;
            };
            RateLimit: {
                threshold: number;
                type: components["schemas"]["LimitType"];
                unit: components["schemas"]["RateLimitUnit"];
            };
            RateLimitUnit: "SECOND"
            | "MINUTE";
            RecreateTrainingJobResponse: {
                training_job: components["schemas"]["TrainingJob"];
            };
            Region: { display_name: string; slug: string };
            Regions: { regions: components["schemas"]["Region"][] };
            RegisterAPIKeyRequest: { key: string; name?: string | null };
            RegisterAPIKeyResponse: { ok: boolean };
            RegistrySecretDockerAuth: {
                secret_ref: components["schemas"]["SecretReference"];
            };
            RequestBackpressurePolicy: "QUEUE_ON_FULL"
            | "REJECT_ON_FULL";
            RequestBackpressureSettings: {
                policy: components["schemas"]["RequestBackpressurePolicy"] | null;
            };
            ResourceKind: | "LOOPS_SAMPLER"
            | "LOOPS_TRAINER"
            | "MODEL_DEPLOYMENT"
            | "TRAINING_JOB"
            | "CHAINLET";
            ResponseTimeDatapoint: {
                p50: number
                | null;
                p95: number | null;
                p99: number | null;
                timestamp: string;
            };
            RestoreVolumeVersionRequest: { expected_sequence?: number
            | null };
            RestoreVolumeVersionResponse: {
                digest: string;
                lifecycle: string;
                namespace: string;
                version_ref: string;
                volume: string;
                volume_sequence: number;
            };
            RetryDeploymentResponse: {
                deployment: components["schemas"]["Deployment"];
                reason: string
                | null;
                retried: boolean;
            };
            RollingDeployConfig: {
                max_surge_percent: number;
                max_unavailable_percent: number;
                replica_overhead_percent: number;
                rolling_deploy_strategy: components["schemas"]["RollingDeployStrategy"];
                stabilization_time_seconds: number;
            };
            RollingDeployStrategy: "REPLICA";
            SearchTrainingJobsRequest: {
                job_id?: string
                | null;
                order_by?: components["schemas"]["OrderBy"][];
                project_id?: string | null;
                statuses?: string[] | null;
            };
            SearchTrainingJobsResponse: {
                training_jobs: components["schemas"]["TrainingJob"][];
            };
            Secret: {
                created_at: string;
                id: string;
                name: string;
                team_name: string;
            };
            SecretReference: { name: string };
            Secrets: { secrets: components["schemas"]["Secret"][] };
            SecretTombstone: { name: string };
            SharedEndpointRegion: "UNRESTRICTED" | "EU";
            SignalPromotionResponse: { success: boolean };
            SignSSHCertificateRequest: {
                public_key: string;
                replica_id?: string | null;
            };
            SignSSHCertificateResponse: {
                jwt: string;
                proxy_address: string;
                ssh_cert_expires_at: string;
                ssh_certificate: string;
            };
            SortOrder: "asc"
            | "desc";
            StopTrainingJobRequest: Record<string, unknown>;
            StopTrainingJobResponse: {
                training_job: components["schemas"]["TrainingJob"];
            };
            StorageMetrics: {
                usage_bytes: components["schemas"]["TrainingJobMetric"][];
                utilization: components["schemas"]["TrainingJobMetric"][];
            };
            SupportedModel: {
                max_context_length: number;
                model_name: string;
                supports_vision_language: boolean;
            };
            SyncDeploymentPatchesRequest: Record<string, unknown>;
            SyncDeploymentPatchesResponse: { needs_full_deploy_reason: string | null };
            Team: { created_at: string; default: boolean; id: string; name: string };
            Teams: { teams: components["schemas"]["Team"][] };
            TeamTrainingGpuCapacityItem: {
                baseline: number;
                dedicated_usage_count: number;
                gpu_type: string;
                limit: number;
                spot_usage_count: number;
                team_id: string;
                team_name: string;
                usage_count: number;
            };
            TerminateReplicaResponse: { success: boolean };
            TrainerCheckpointTarget: "sampler" | "trainer";
            TrainingGpuCapacityItem: {
                baseline: number;
                dedicated_usage_count: number;
                gpu_type: string;
                limit: number;
                spot_usage_count: number;
                usage_count: number;
            };
            TrainingItem: {
                billable_resource: components["schemas"]["BillableResource"];
                daily?: components["schemas"]["DailyTrainingUsage"][];
                minutes: number;
                subtotal: number
                | string;
            };
            TrainingJob: {
                availability_model: components["schemas"]["V1AvailabilityModel"];
                checkpoint_sync_status: | components["schemas"]["CheckpointSyncStatus"]
                | null;
                created_at: string;
                current_status: string;
                error_message: string
                | null;
                id: string;
                instance_type: components["schemas"]["InstanceType"];
                name: string | null;
                node_count: number;
                priority: number;
                training_project: components["schemas"]["TrainingProjectSummary"];
                training_project_id: string;
                updated_at: string;
                user: components["schemas"]["User"] | null;
            };
            TrainingJobCheckpoint: {
                base_model: string
                | null;
                checkpoint_id: string;
                checkpoint_type: string;
                created_at: string;
                lora_adapter_config: { [key: string]: unknown } | null;
                size_bytes: number;
                sync_status: string | null;
                training_job_id: string;
            };
            TrainingJobMetric: { timestamp: string; value: number };
            TrainingJobMetrics: {
                cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
                cpu_usage: components["schemas"]["TrainingJobMetric"][];
                ephemeral_storage: components["schemas"]["StorageMetrics"];
                gpu_memory_usage_bytes: {
                    [key: string]: { timestamp: string; value: number }[];
                };
                gpu_utilization: {
                    [key: string]: { timestamp: string; value: number }[];
                };
            };
            TrainingJobNodeMetrics: {
                metrics: components["schemas"]["TrainingJobMetrics"];
                node_id: string;
            };
            TrainingJobTombstone: {
                deleted: boolean;
                id: string;
                training_project_id: string;
            };
            TrainingProject: {
                created_at: string;
                id: string;
                latest_job: components["schemas"]["TrainingJob"]
                | null;
                name: string;
                team_name: string | null;
                updated_at: string;
            };
            TrainingProjectSummary: { id: string; name: string };
            TrainingProjectTombstone: { deleted: boolean; id: string };
            TrainingUsage: {
                breakdown?: components["schemas"]["TrainingItem"][];
                credits_used: number | string;
                minutes: number;
                subtotal: number | string;
                total: number | string;
            };
            TrainingWeightAuth: {
                auth_method: components["schemas"]["AuthMethod"];
                auth_secret_name?: string
                | null;
                aws_assume_role_arn?: string | null;
                aws_assume_role_region?: string | null;
                aws_oidc_region?: string | null;
                aws_oidc_role_arn?: string | null;
                gcp_oidc_service_account?: string | null;
                gcp_oidc_workload_id_provider?: string | null;
            };
            TrussUserEnv: {
                git_info?: components["schemas"]["GitInfo"]
                | null;
                is_frontend_deployment?: boolean;
                is_library_deployment?: boolean;
                mypy_version?: string | null;
                pydantic_version?: string | null;
                python_version?: string | null;
                truss_client_version?: string | null;
            };
            TTSBenchmarkMetrics: {
                cost_per_audio_minute_usd?: number
                | null;
                max_concurrent_streams_at_rtf1?: number | null;
                ttft_ms_p50?: number | null;
                ttft_ms_p50_at_max_concurrency?: number | null;
            };
            UpdateAutoscalingScheduleSettings: {
                delete_schedules?: string[];
                schedules?: (
                    | components["schemas"]["AutoscalingScheduleUpsert"]
                    | components["schemas"]["OneTimeAutoscalingScheduleUpsert"]
                )[];
                timezone?: string
                | null;
            };
            UpdateAutoscalingSettings: {
                autoscaling_window?: number
                | null;
                concurrency_target?: number | null;
                max_replica?: number | null;
                max_scale_down_rate?: number | null;
                min_replica?: number | null;
                scale_down_delay?: number | null;
                target_in_flight_tokens?: number | null;
                target_utilization_percentage?: number | null;
            };
            UpdateAutoscalingSettingsResponse: {
                message: string;
                status: components["schemas"]["UpdateAutoscalingSettingsStatus"];
            };
            UpdateAutoscalingSettingsStatus: "ACCEPTED"
            | "QUEUED"
            | "UNCHANGED";
            UpdateChainEnvironmentRequest: {
                promotion_settings?:
                    | components["schemas"]["UpdatePromotionSettings"]
                    | null;
            };
            UpdateChainEnvironmentResponse: { ok: boolean };
            UpdateChainletEnvironmentAutoscalingSettingsRequest: {
                updates: components["schemas"]["ChainletEnvironmentAutoscalingSettingsUpdate"][];
            };
            UpdateChainletEnvironmentInstanceTypeRequest: {
                updates: components["schemas"]["ChainletEnvironmentInstanceTypeUpdate"][];
            };
            UpdateChainletEnvironmentInstanceTypeResponse: {
                chain_deployment: components["schemas"]["ChainDeployment"]
                | null;
                chainlet_environment_settings: components["schemas"]["ChainletEnvironmentSettings"][];
                requires_redeployment: boolean;
            };
            UpdateDeploymentRequest: { name?: string
            | null };
            UpdateEndpointRequest: {
                targets?: components["schemas"]["EndpointTargetRequest"][] | null;
            };
            UpdateEnvironmentGroupManageAccess: {
                is_restricted: boolean;
                user_ids?: string[];
            };
            UpdateEnvironmentGroupRequest: {
                manage_access?: | components["schemas"]["UpdateEnvironmentGroupManageAccess"]
                | null;
            };
            UpdateEnvironmentRequest: {
                autoscaling_schedule_settings?: | components["schemas"]["UpdateAutoscalingScheduleSettings"]
                | null;
                autoscaling_settings?: | components["schemas"]["UpdateAutoscalingSettings"]
                | null;
                promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
                | null;
                request_backpressure_settings?: | components["schemas"]["UpdateRequestBackpressureSettings"]
                | null;
            };
            UpdateEnvironmentResponse: {
                environment: components["schemas"]["Environment"];
                message: string;
                status: components["schemas"]["UpdateAutoscalingSettingsStatus"];
            };
            UpdateGroupMetadata: { name?: string
            | null };
            UpdateGroupRequest: {
                metadata?: components["schemas"]["UpdateGroupMetadata"] | null;
                models?: components["schemas"]["ModelConfig"][] | null;
            };
            UpdateLibraryListingRequest: {
                display_name?: string
                | null;
                is_public?: boolean | null;
                metadata?: components["schemas"]["LibraryListingMetadata"] | null;
                trending?: boolean | null;
            };
            UpdateLibraryListingVersionRequest: {
                allow_truss_download?: boolean
                | null;
                benchmark?: components["schemas"]["BenchmarkSnapshot"] | null;
                is_live?: boolean | null;
            };
            UpdatePromotionSettings: {
                promotion_cleanup_strategy?: | components["schemas"]["PromotionCleanupStrategy"]
                | null;
                ramp_up_duration_seconds?: number
                | null;
                ramp_up_while_promoting?: boolean | null;
                redeploy_on_promotion?: boolean | null;
                rolling_deploy?: boolean | null;
                rolling_deploy_config?:
                    | components["schemas"]["UpdateRollingDeployConfig"]
                    | null;
            };
            UpdateRequestBackpressureSettings: {
                policy?: components["schemas"]["RequestBackpressurePolicy"]
                | null;
            };
            UpdateRollingDeployConfig: {
                max_surge_percent?: number
                | null;
                max_unavailable_percent?: number | null;
                replica_overhead_percent?: number | null;
                rolling_deploy_strategy?:
                    | components["schemas"]["RollingDeployStrategy"]
                    | null;
                stabilization_time_seconds?: number
                | null;
            };
            UpdateTrainingJobRequest: {
                availability_model?: | components["schemas"]["V1AvailabilityModel"]
                | null;
                priority?: number
                | null;
            };
            UpdateTrainingJobResponse: {
                training_job: components["schemas"]["TrainingJob"];
            };
            UpsertSecretRequest: { name: string; value: string };
            UpsertTrainingProject: { name: string };
            UpsertTrainingProjectRequest: {
                training_project: components["schemas"]["UpsertTrainingProject"];
            };
            UpsertTrainingProjectResponse: {
                training_project: components["schemas"]["TrainingProject"];
            };
            UsageDimension: "api_key"
            | "user"
            | "model";
            UsageLimit: {
                threshold: number;
                type: components["schemas"]["LimitType"];
                unit: components["schemas"]["UsageLimitUnit"];
            };
            UsageLimitUnit: "DAY";
            UsageSummary: {
                dedicated_usage: components["schemas"]["DedicatedUsage"]
                | null;
                model_apis_usage: components["schemas"]["ModelApisUsage"] | null;
                training_usage: components["schemas"]["TrainingUsage"] | null;
            };
            User: { email: string
            | null };
            UserInfo: {
                email: string | null;
                name: string | null;
                user_id: string;
                workspace_name: string | null;
            };
            UsersResponse: {
                items: components["schemas"]["UserInfo"][];
                pagination: components["schemas"]["PaginationResponse"];
            };
            V1AvailabilityModel: "dedicated"
            | "spot";
            V1InteractiveSessionAuthProvider: "github" | "microsoft";
            V1InteractiveSessionProvider: "vs_code" | "cursor" | "ssh";
            V1InteractiveSessionTrigger: "on_startup" | "on_failure" | "on_demand";
            ValidateLoopsCheckpointRequest: { checkpoint_path: string };
            ValidateLoopsCheckpointResponse: Record<string, unknown>;
            VertexTargetConfig: { location: string; project_id: string };
            Volume: {
                head: components["schemas"]["VolumeVersionSummary"] | null;
                name: string;
                namespace: string;
                sequence: number;
                tag_count: number;
                tags: components["schemas"]["VolumeTag"][];
                updated_at: string;
                version_ref: string;
                versions_alive: number;
                versions_tombstoned: number;
                versions_untagged: number;
            };
            VolumeTag: { digest: string; name: string };
            VolumeTokenScope: "PULL" | "INSPECT" | "PUSH" | "TAG";
            VolumeVersion: {
                created_at: string;
                delete_after: string | null;
                digest: string;
                is_head: boolean;
                lifecycle: string;
                namespace: string;
                sequence: number | null;
                tags: string[];
                tombstoned_at: string | null;
                total_size_bytes: number | null;
                version_ref: string;
                volume: string;
            };
            VolumeVersionDetail: {
                created_at: string;
                delete_after: string
                | null;
                digest: string;
                entry_count: number | null;
                is_head: boolean;
                lifecycle: string;
                namespace: string;
                sequence: number | null;
                tags: string[];
                tombstoned_at: string | null;
                total_size_bytes: number | null;
                version_ref: string;
                volume: string;
                volume_sequence: number;
            };
            VolumeVersionSummary: {
                created_at: string;
                digest: string;
                total_size_bytes: number;
            };
        };
    }
    Index
    headers: never
    parameters: {
        api_key_prefix: string;
        chain_deployment_id: string;
        chain_id: string;
        chainlet_id: string;
        checkpoint_id: string;
        deployment_id: string;
        endpoint_id: string;
        env_name: string;
        group_id: string;
        model_api_name: string;
        model_id: string;
        replica_id: string;
        run_id: string;
        sampler_id: string;
        secret_name: string;
        session_id: string;
        team_id: string;
        training_job_id: string;
        training_project_id: string;
        user_defined_listing_id: string;
        user_id: string;
        version_tag: string;
        volume_name: string;
        volume_namespace: string;
        volume_version: string;
    }
    pathItems: never
    requestBodies: never
    responses: never
    schemas: {
        ActivateResponse: { no_op: boolean; success: boolean };
        ActiveJobAtSubmit: {
            instance_type_name: string;
            status_at_submit: string;
            status_set_at: string;
            total_gpus: number;
            training_job_id: string;
            training_job_name: string | null;
            workload_plane_name: string;
        };
        APIKey: { api_key: string };
        APIKeyCategory:
            | "PERSONAL"
            | "ROUTES"
            | "WORKSPACE_MANAGE_ALL"
            | "WORKSPACE_EXPORT_METRICS"
            | "WORKSPACE_INVOKE"
            | "WORKSPACE_MANAGE_API_KEYS";
        APIKeyInfo: {
            model_ids: string[]
            | null;
            name: string | null;
            owner: components["schemas"]["APIKeyOwner"] | null;
            prefix: string;
            team_name: string | null;
            type: components["schemas"]["APIKeyCategory"];
        };
        APIKeyOwner: { email: string
        | null; name: string | null; user_id: string };
        APIKeys: { keys: components["schemas"]["APIKeyInfo"][] };
        APIKeyTombstone: { prefix: string };
        AuditLogActor: {
            api_key_name: string | null;
            api_key_prefix: string | null;
            email: string | null;
            type: components["schemas"]["AuditLogActorType"];
        };
        AuditLogActorType: | "USER"
        | "API_KEY"
        | "BASETEN_USER"
        | "BASETEN_SYSTEM"
        | "TOMBSTONE_USER";
        AuditLogApiKeyType: | "PERSONAL"
        | "CREATOR_SERVICE_ACCOUNT"
        | "MANAGE_API_KEYS_SERVICE_ACCOUNT"
        | "INVOKE_ALL_MODELS_SERVICE_ACCOUNT"
        | "INVOKE_ALLOWED_MODELS_SERVICE_ACCOUNT"
        | "INVOKE_SCOPED_ENVS_AND_MODELS_SERVICE_ACCOUNT"
        | "EXPORT_METRICS_ALL_MODELS_SERVICE_ACCOUNT"
        | "EXPORT_METRICS_ALLOWED_MODELS_SERVICE_ACCOUNT"
        | "INVOKE_ALL_SHARED_ENDPOINTS_SERVICE_ACCOUNT"
        | "INVOKE_ALLOWED_SHARED_ENDPOINTS_SERVICE_ACCOUNT"
        | "INVOKE_ALL_ROUTES";
        AuditLogEntry: {
            actor: components["schemas"]["AuditLogActor"];
            client_name: string
            | null;
            client_session_id: string | null;
            client_version: string | null;
            created: string;
            event_data:
                | components["schemas"]["AuditLogEventModelDeployed"]
                | components["schemas"]["AuditLogEventModelDeploymentActivated"]
                | components["schemas"]["AuditLogEventModelDeploymentDeactivated"]
                | components["schemas"]["AuditLogEventModelDeploymentRetried"]
                | components["schemas"]["AuditLogEventModelDeploymentPromoted"]
                | components["schemas"]["AuditLogEventModelDeploymentAutoscalingSettingsChanged"]
                | components["schemas"]["AuditLogEventModelDeploymentRequestBackpressureSettingsChanged"]
                | components["schemas"]["AuditLogEventModelDeploymentInstanceTypeChanged"]
                | components["schemas"]["AuditLogEventModelDeploymentDeleted"]
                | components["schemas"]["AuditLogEventModelDeleted"]
                | components["schemas"]["AuditLogEventChainDeployed"]
                | components["schemas"]["AuditLogEventChainDeploymentActivated"]
                | components["schemas"]["AuditLogEventChainDeploymentDeactivated"]
                | components["schemas"]["AuditLogEventChainDeploymentPromoted"]
                | components["schemas"]["AuditLogEventChainletAutoscalingSettingsChanged"]
                | components["schemas"]["AuditLogEventChainletInstanceTypeChanged"]
                | components["schemas"]["AuditLogEventChainDeploymentDeleted"]
                | components["schemas"]["AuditLogEventChainDeleted"]
                | components["schemas"]["AuditLogEventChainEnvironmentCreated"]
                | components["schemas"]["AuditLogEventChainEnvironmentUpdated"]
                | components["schemas"]["AuditLogEventSecretUpdated"]
                | components["schemas"]["AuditLogEventSecretDeleted"]
                | components["schemas"]["AuditLogEventApiKeyCreated"]
                | components["schemas"]["AuditLogEventApiKeyDeleted"]
                | components["schemas"]["AuditLogEventGatewayEndpointCreated"]
                | components["schemas"]["AuditLogEventGatewayEndpointUpdated"]
                | components["schemas"]["AuditLogEventGatewayEndpointDeleted"]
                | components["schemas"]["AuditLogEventUserInvited"]
                | components["schemas"]["AuditLogEventUserJoinedOrganization"]
                | components["schemas"]["AuditLogEventWebhookSigningSecretCreated"]
                | components["schemas"]["AuditLogEventWebhookSigningSecretRotated"]
                | components["schemas"]["AuditLogEventWebhookSigningSecretDeleted"]
                | components["schemas"]["AuditLogEventUserRoleUpdated"]
                | components["schemas"]["AuditLogEventUserTeamRoleUpdated"]
                | components["schemas"]["AuditLogEventUserRemoved"]
                | components["schemas"]["AuditLogEventDirectoryGroupRoleUpdated"]
                | components["schemas"]["AuditLogEventRequireGroupBasedAdminsEnabled"]
                | components["schemas"]["AuditLogEventEnvironmentCreated"]
                | components["schemas"]["AuditLogEventEnvironmentUpdated"]
                | components["schemas"]["AuditLogEventEnvironmentDeleted"]
                | components["schemas"]["AuditLogEventReplicaTerminated"]
                | components["schemas"]["AuditLogEventModelPromotionControlAction"]
                | components["schemas"]["AuditLogEventSshCertificateSigned"]
                | components["schemas"]["AuditLogEventVolumeDeleted"]
                | components["schemas"]["AuditLogEventVolumeVersionDeleted"]
                | components["schemas"]["AuditLogEventVolumeVersionRestored"];
            event_type: components["schemas"]["AuditLogEventType"];
            id: string;
            source: components["schemas"]["AuditLogSource"]
            | null;
        };
        AuditLogEventApiKeyCreated: {
            api_key_id: string;
            api_key_type: components["schemas"]["AuditLogApiKeyType"];
            event_type: "API_KEY_CREATED";
            prefix: string;
        };
        AuditLogEventApiKeyDeleted: {
            api_key_id: string;
            api_key_type: components["schemas"]["AuditLogApiKeyType"];
            event_type: "API_KEY_DELETED";
            prefix: string;
        };
        AuditLogEventAutoscalingScheduleAction: | "CREATED"
        | "UPDATED"
        | "DELETED"
        | "UNCHANGED";
        AuditLogEventAutoscalingScheduleChange: {
            action: components["schemas"]["AuditLogEventAutoscalingScheduleAction"];
            current: | components["schemas"]["AuditLogEventAutoscalingScheduleSettings"]
            | null;
            previous: | components["schemas"]["AuditLogEventAutoscalingScheduleSettings"]
            | null;
            schedule_id: string;
        };
        AuditLogEventAutoscalingScheduleSettings: {
            autoscaling_window: number
            | null;
            cadence: string;
            concurrency_target: number | null;
            enabled: boolean;
            end_at: string | null;
            end_hour: number | null;
            end_minute: number | null;
            max_replica: number;
            max_scale_down_rate: number | null;
            min_replica: number;
            scale_down_delay: number | null;
            schedule_name: string;
            start_at: string | null;
            start_hour: number | null;
            start_minute: number | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
            timezone: string;
            weekdays: string[] | null;
        };
        AuditLogEventAutoscalingSettings: {
            autoscaling_window: number
            | null;
            concurrency_target: number;
            max_replica: number;
            max_scale_down_rate: number | null;
            min_replica: number;
            scale_down_delay: number | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AuditLogEventChainDeleted: {
            chain_deployment_name: string
            | null;
            chain_id: string;
            chain_name: string;
            event_type: "CHAIN_DELETED";
        };
        AuditLogEventChainDeployed: {
            chain_deployment_id: string;
            chain_deployment_name: string
            | null;
            chain_id: string;
            chain_name: string;
            event_type: "CHAIN_DEPLOYED";
            is_primary: boolean;
            publish: boolean;
        };
        AuditLogEventChainDeploymentActivated: {
            chain_deployment_id: string;
            chain_deployment_name: string
            | null;
            chain_id: string;
            chain_name: string;
            event_type: "CHAIN_DEPLOYMENT_ACTIVATED";
        };
        AuditLogEventChainDeploymentDeactivated: {
            chain_deployment_id: string;
            chain_deployment_name: string
            | null;
            chain_id: string;
            chain_name: string;
            event_type: "CHAIN_DEPLOYMENT_DEACTIVATED";
        };
        AuditLogEventChainDeploymentDeleted: {
            chain_deployment_id: string;
            chain_id: string;
            chain_name: string;
            deployment_name: string
            | null;
            event_type: "CHAIN_DEPLOYMENT_DELETED";
        };
        AuditLogEventChainDeploymentPromoted: {
            chain_deployment_id: string;
            chain_deployment_name: string
            | null;
            chain_id: string;
            chain_name: string;
            environment_id: string | null;
            environment_name: string | null;
            event_type: "CHAIN_DEPLOYMENT_PROMOTED";
        };
        AuditLogEventChainEnvironmentCreated: {
            chain_id: string;
            chain_name: string;
            environment_name: string;
            event_type: "CHAIN_ENVIRONMENT_CREATED";
            ramp_up_duration_seconds: number
            | null;
            ramp_up_while_promoting: boolean | null;
            redeploy_on_promotion: boolean | null;
        };
        AuditLogEventChainEnvironmentUpdated: {
            chain_id: string;
            chain_name: string;
            environment_name: string;
            event_type: "CHAIN_ENVIRONMENT_UPDATED";
            ramp_up_duration_seconds: number
            | null;
            ramp_up_while_promoting: boolean | null;
            redeploy_on_promotion: boolean | null;
        };
        AuditLogEventChainletAutoscalingSettingsChanged: {
            autoscaling_window: number
            | null;
            chain_deployment_id: string;
            chain_deployment_name: string | null;
            chain_id: string;
            chain_name: string;
            chainlet_id: string;
            chainlet_name: string;
            concurrency_target: number;
            event_type: "CHAINLET_AUTOSCALING_SETTINGS_CHANGED";
            max_replica: number;
            max_scale_down_rate: number | null;
            min_replica: number;
            previous_settings:
                | components["schemas"]["AuditLogEventAutoscalingSettings"]
                | null;
            scale_down_delay: number
            | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AuditLogEventChainletInstanceTypeChanged: {
            chain_deployment_id: string;
            chain_deployment_name: string
            | null;
            chain_id: string;
            chain_name: string;
            chainlet_id: string;
            chainlet_name: string;
            event_type: "CHAINLET_INSTANCE_TYPE_CHANGED";
            instance_type_name: string;
        };
        AuditLogEventDirectoryGroupRoleUpdated: {
            directory_group_id: string;
            directory_group_name: string;
            event_type: "DIRECTORY_GROUP_ROLE_UPDATED";
            new_role_name: string;
            team_id: string
            | null;
            team_name: string | null;
        };
        AuditLogEventEnvironmentCreated: {
            autoscaling_window: number
            | null;
            concurrency_target: number;
            deployment_type: string | null;
            environment_name: string;
            event_type: "ENVIRONMENT_CREATED";
            max_replica: number;
            max_scale_down_rate: number | null;
            max_surge_percent: number | null;
            max_unavailable_percent: number | null;
            min_replica: number;
            model_id: string;
            model_name: string;
            promotion_cleanup_strategy: string | null;
            ramp_up_duration_seconds: number | null;
            ramp_up_step_size: number | null;
            ramp_up_while_promoting: boolean | null;
            redeploy_on_promotion: boolean | null;
            replica_overhead_percent: number | null;
            request_backpressure_policy: string | null;
            rolling_deploy: boolean | null;
            rolling_deploy_strategy: string | null;
            scale_down_delay: number | null;
            stabilization_time_seconds: number | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AuditLogEventEnvironmentDeleted: {
            environment_name: string;
            event_type: "ENVIRONMENT_DELETED";
            model_id: string;
            model_name: string;
        };
        AuditLogEventEnvironmentSettings: {
            autoscaling_window: number
            | null;
            concurrency_target: number;
            max_replica: number;
            max_scale_down_rate: number | null;
            max_surge_percent: number | null;
            max_unavailable_percent: number | null;
            min_replica: number;
            promotion_cleanup_strategy: string | null;
            ramp_up_duration_seconds: number | null;
            ramp_up_step_size: number | null;
            ramp_up_while_promoting: boolean | null;
            redeploy_on_promotion: boolean | null;
            replica_overhead_percent: number | null;
            request_backpressure_policy: string | null;
            rolling_deploy: boolean | null;
            rolling_deploy_strategy: string | null;
            scale_down_delay: number | null;
            stabilization_time_seconds: number | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AuditLogEventEnvironmentUpdated: {
            autoscaling_window: number
            | null;
            concurrency_target: number;
            deployment_type: string | null;
            environment_name: string;
            event_type: "ENVIRONMENT_UPDATED";
            max_replica: number;
            max_scale_down_rate: number | null;
            max_surge_percent: number | null;
            max_unavailable_percent: number | null;
            min_replica: number;
            model_id: string;
            model_name: string;
            previous_settings:
                | components["schemas"]["AuditLogEventEnvironmentSettings"]
                | null;
            promotion_cleanup_strategy: string
            | null;
            ramp_up_duration_seconds: number | null;
            ramp_up_step_size: number | null;
            ramp_up_while_promoting: boolean | null;
            redeploy_on_promotion: boolean | null;
            replica_overhead_percent: number | null;
            request_backpressure_policy: string | null;
            rolling_deploy: boolean | null;
            rolling_deploy_strategy: string | null;
            scale_down_delay: number | null;
            schedules:
                | components["schemas"]["AuditLogEventAutoscalingScheduleChange"][]
                | null;
            stabilization_time_seconds: number
            | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AuditLogEventGatewayEndpointCreated: {
            event_type: "GATEWAY_ENDPOINT_CREATED";
            gateway_endpoint_id: string;
            slug: string;
        };
        AuditLogEventGatewayEndpointDeleted: {
            event_type: "GATEWAY_ENDPOINT_DELETED";
            gateway_endpoint_id: string;
            slug: string;
        };
        AuditLogEventGatewayEndpointUpdated: {
            event_type: "GATEWAY_ENDPOINT_UPDATED";
            gateway_endpoint_id: string;
            previous_slug: string
            | null;
            slug: string;
        };
        AuditLogEventModelDeleted: {
            event_type: "MODEL_DELETED";
            model_id: string;
            model_name: string;
        };
        AuditLogEventModelDeployed: {
            deployment_id: string;
            deployment_name: string;
            environment_name: string
            | null;
            event_type: "MODEL_DEPLOYED";
            model_id: string;
            model_name: string;
            publish: boolean;
            scale_previous_to_zero: boolean;
            trusted: boolean;
        };
        AuditLogEventModelDeploymentActivated: {
            deployment_id: string;
            deployment_name: string;
            event_type: "MODEL_DEPLOYMENT_ACTIVATED";
            model_id: string;
            model_name: string;
        };
        AuditLogEventModelDeploymentAutoscalingSettingsChanged: {
            autoscaling_window: number
            | null;
            concurrency_target: number;
            deployment_id: string;
            deployment_name: string;
            deployment_type: string | null;
            event_type: "MODEL_DEPLOYMENT_AUTOSCALING_SETTINGS_CHANGED";
            max_replica: number;
            max_scale_down_rate: number | null;
            min_replica: number;
            model_id: string;
            model_name: string;
            previous_settings:
                | components["schemas"]["AuditLogEventAutoscalingSettings"]
                | null;
            scale_down_delay: number
            | null;
            schedules:
                | components["schemas"]["AuditLogEventAutoscalingScheduleChange"][]
                | null;
            target_in_flight_tokens: number
            | null;
            target_utilization_percentage: number | null;
        };
        AuditLogEventModelDeploymentDeactivated: {
            deployment_id: string;
            deployment_name: string;
            event_type: "MODEL_DEPLOYMENT_DEACTIVATED";
            model_id: string;
            model_name: string;
        };
        AuditLogEventModelDeploymentDeleted: {
            deployment_id: string;
            deployment_name: string;
            event_type: "MODEL_DEPLOYMENT_DELETED";
            model_id: string;
            model_name: string;
        };
        AuditLogEventModelDeploymentInstanceTypeChanged: {
            deployment_id: string;
            deployment_name: string;
            event_type: "MODEL_DEPLOYMENT_INSTANCE_TYPE_CHANGED";
            instance_type_name: string;
            model_id: string;
            model_name: string;
        };
        AuditLogEventModelDeploymentPromoted: {
            deployment_id: string;
            deployment_name: string;
            environment_id: string
            | null;
            environment_name: string | null;
            event_type: "MODEL_DEPLOYMENT_PROMOTED";
            model_id: string;
            model_name: string;
        };
        AuditLogEventModelDeploymentRequestBackpressureSettingsChanged: {
            deployment_id: string;
            deployment_name: string;
            event_type: "MODEL_DEPLOYMENT_REQUEST_BACKPRESSURE_SETTINGS_CHANGED";
            model_id: string;
            model_name: string;
            policy: string
            | null;
            previous_policy: string | null;
        };
        AuditLogEventModelDeploymentRetried: {
            deployment_id: string;
            deployment_name: string;
            event_type: "MODEL_DEPLOYMENT_RETRIED";
            model_id: string;
            model_name: string;
            retried: boolean;
        };
        AuditLogEventModelPromotionControlAction: {
            action: components["schemas"]["AuditLogPromotionControlAction"];
            deployment_id: string;
            deployment_name: string;
            environment_id: string
            | null;
            environment_name: string;
            event_type: "MODEL_PROMOTION_CONTROL_ACTION";
            model_id: string;
            model_name: string;
        };
        AuditLogEventReplicaTerminated: {
            deployment_id: string;
            deployment_name: string;
            event_type: "REPLICA_TERMINATED";
            model_id: string;
            model_name: string;
            replica_id: string;
        };
        AuditLogEventRequireGroupBasedAdminsEnabled: {
            event_type: "REQUIRE_GROUP_BASED_ADMINS_ENABLED";
            organization_id: string;
        };
        AuditLogEventSecretDeleted: {
            event_type: "SECRET_DELETED";
            secret_id: string;
            secret_name: string;
        };
        AuditLogEventSecretUpdated: {
            event_type: "SECRET_UPDATED";
            secret_id: string;
            secret_name: string;
        };
        AuditLogEventSshCertificateSigned: {
            event_type: "SSH_CERTIFICATE_SIGNED";
            expires_at: string;
            project_id: string;
            proxy_address: string;
            replica_id: string;
            workload_id: string;
            workload_type: string;
        };
        AuditLogEventType: | "MODEL_DEPLOYED"
        | "MODEL_DEPLOYMENT_ACTIVATED"
        | "MODEL_DEPLOYMENT_DEACTIVATED"
        | "MODEL_DEPLOYMENT_RETRIED"
        | "MODEL_DEPLOYMENT_PROMOTED"
        | "MODEL_DEPLOYMENT_AUTOSCALING_SETTINGS_CHANGED"
        | "MODEL_DEPLOYMENT_REQUEST_BACKPRESSURE_SETTINGS_CHANGED"
        | "MODEL_DEPLOYMENT_INSTANCE_TYPE_CHANGED"
        | "MODEL_DEPLOYMENT_DELETED"
        | "MODEL_DELETED"
        | "CHAIN_DEPLOYED"
        | "CHAIN_DEPLOYMENT_ACTIVATED"
        | "CHAIN_DEPLOYMENT_DEACTIVATED"
        | "CHAIN_DEPLOYMENT_PROMOTED"
        | "CHAINLET_AUTOSCALING_SETTINGS_CHANGED"
        | "CHAINLET_INSTANCE_TYPE_CHANGED"
        | "CHAIN_DEPLOYMENT_DELETED"
        | "CHAIN_DELETED"
        | "CHAIN_ENVIRONMENT_CREATED"
        | "CHAIN_ENVIRONMENT_UPDATED"
        | "SECRET_UPDATED"
        | "SECRET_DELETED"
        | "API_KEY_CREATED"
        | "API_KEY_DELETED"
        | "GATEWAY_ENDPOINT_CREATED"
        | "GATEWAY_ENDPOINT_UPDATED"
        | "GATEWAY_ENDPOINT_DELETED"
        | "USER_INVITED"
        | "USER_JOINED_ORGANIZATION"
        | "WEBHOOK_SIGNING_SECRET_CREATED"
        | "WEBHOOK_SIGNING_SECRET_ROTATED"
        | "WEBHOOK_SIGNING_SECRET_DELETED"
        | "USER_ROLE_UPDATED"
        | "USER_TEAM_ROLE_UPDATED"
        | "USER_REMOVED"
        | "DIRECTORY_GROUP_ROLE_UPDATED"
        | "REQUIRE_GROUP_BASED_ADMINS_ENABLED"
        | "ENVIRONMENT_CREATED"
        | "ENVIRONMENT_UPDATED"
        | "ENVIRONMENT_DELETED"
        | "REPLICA_TERMINATED"
        | "MODEL_PROMOTION_CONTROL_ACTION"
        | "SSH_CERTIFICATE_SIGNED"
        | "VOLUME_DELETED"
        | "VOLUME_VERSION_DELETED"
        | "VOLUME_VERSION_RESTORED";
        AuditLogEventTypeGroup: | "DEPLOYED"
        | "PROMOTED"
        | "ACTIVATED_DEACTIVATED"
        | "AUTOSCALING_SETTINGS"
        | "REQUEST_BACKPRESSURE_SETTINGS"
        | "INSTANCE_TYPE_CHANGED"
        | "ENVIRONMENT_SETTINGS"
        | "REPLICA_TERMINATED"
        | "DELETED"
        | "SECRETS"
        | "API_KEYS"
        | "GATEWAY"
        | "WEBHOOK_SIGNING_SECRETS"
        | "USER_MANAGEMENT"
        | "DIRECTORY_GROUP_MANAGEMENT"
        | "SSH";
        AuditLogEventUserInvited: {
            event_type: "USER_INVITED";
            invited_user_email: string;
            role_name: string;
        };
        AuditLogEventUserJoinedOrganization: {
            event_type: "USER_JOINED_ORGANIZATION";
            new_user_email: string;
            user_id: string;
        };
        AuditLogEventUserRemoved: {
            event_type: "USER_REMOVED";
            removed_user_email: string;
        };
        AuditLogEventUserRoleUpdated: {
            event_type: "USER_ROLE_UPDATED";
            new_role_name: string;
            user_email: string;
            user_id: string;
        };
        AuditLogEventUserTeamRoleUpdated: {
            event_type: "USER_TEAM_ROLE_UPDATED";
            new_role_name: string;
            team_id: string;
            team_name: string;
            user_email: string;
            user_id: string;
        };
        AuditLogEventVolumeDeleted: {
            event_type: "VOLUME_DELETED";
            namespace: string;
            versions_deleted: number;
            volume_name: string;
            volume_ref: string;
        };
        AuditLogEventVolumeVersionDeleted: {
            digest: string;
            event_type: "VOLUME_VERSION_DELETED";
            namespace: string;
            version: string;
            volume_name: string;
            volume_ref: string;
        };
        AuditLogEventVolumeVersionRestored: {
            digest: string;
            event_type: "VOLUME_VERSION_RESTORED";
            namespace: string;
            version: string;
            volume_name: string;
            volume_ref: string;
        };
        AuditLogEventWebhookSigningSecretCreated: {
            event_type: "WEBHOOK_SIGNING_SECRET_CREATED";
            webhook_signing_secret_id: string;
        };
        AuditLogEventWebhookSigningSecretDeleted: {
            event_type: "WEBHOOK_SIGNING_SECRET_DELETED";
            webhook_signing_secret_id: string;
        };
        AuditLogEventWebhookSigningSecretRotated: {
            event_type: "WEBHOOK_SIGNING_SECRET_ROTATED";
            webhook_signing_secret_id: string;
        };
        AuditLogPromotionControlAction: | "PAUSE"
        | "RESUME"
        | "FORCE_CANCEL"
        | "FORCE_ROLL_FORWARD"
        | "GRACEFUL_CANCEL";
        AuditLogSortDirection: "DESC"
        | "ASC";
        AuditLogSource: "UI" | "API" | "MCP" | "SYSTEM" | "OTHER";
        AuthCode: {
            auth_code: string;
            auth_url: string;
            expires_at: string | null;
            generated_at: string | null;
            replica_id: string;
            session_id: string;
            tunnel_name: string | null;
            working_directory: string | null;
        };
        AuthMethod: "CUSTOM_SECRET"
        | "AWS_OIDC"
        | "GCP_OIDC"
        | "AWS_ASSUME_ROLE";
        AutoscalingSchedule: {
            autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"];
            cadence: "DAILY" | "HOURLY";
            enabled: boolean;
            end_hour: number | null;
            end_minute: number;
            id: string;
            name: string;
            start_hour: number | null;
            start_minute: number;
            weekdays: components["schemas"]["AutoscalingScheduleWeekday"][];
        };
        AutoscalingScheduleSettings: {
            autoscaling_window: number
            | null;
            concurrency_target: number | null;
            max_replica: number;
            max_scale_down_rate: number | null;
            min_replica: number;
            scale_down_delay: number | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AutoscalingScheduleSettingsRequest: {
            autoscaling_window: number
            | null;
            concurrency_target: number | null;
            max_replica: number;
            max_scale_down_rate: number | null;
            min_replica: number;
            scale_down_delay: number | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AutoscalingScheduleState: {
            autoscaling_settings: components["schemas"]["AutoscalingSettings"];
            schedule_id: string
            | null;
        };
        AutoscalingScheduleUpsert: {
            autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"];
            cadence: "DAILY"
            | "HOURLY";
            enabled: boolean;
            end_hour?: number | null;
            end_minute: number;
            id?: string | null;
            name: string;
            start_hour?: number | null;
            start_minute: number;
            weekdays: components["schemas"]["AutoscalingScheduleWeekday"][];
        };
        AutoscalingScheduleWeekday: | "SUNDAY"
        | "MONDAY"
        | "TUESDAY"
        | "WEDNESDAY"
        | "THURSDAY"
        | "FRIDAY"
        | "SATURDAY";
        AutoscalingSettings: {
            autoscaling_window: number
            | null;
            concurrency_target: number;
            max_replica: number;
            max_scale_down_rate: number | null;
            min_replica: number;
            scale_down_delay: number | null;
            target_in_flight_tokens: number | null;
            target_utilization_percentage: number | null;
        };
        AwsAssumeRole: { baseten_role_arn: string; external_id: string };
        AwsAssumeRoleDockerAuth: { region: string; role_arn: string };
        AWSCredentials: {
            aws_access_key_id: string;
            aws_secret_access_key: string;
            aws_session_token: string;
        };
        AwsIamDockerAuth: {
            access_key_secret_ref: components["schemas"]["SecretReference"];
            secret_access_key_secret_ref: components["schemas"]["SecretReference"];
        };
        AwsOidcDockerAuth: { region: string; role_arn: string };
        BasetenLatestCheckpointConfig: {
            job_id?: string | null;
            project_name?: string | null;
            typ: "baseten_latest_checkpoint";
        };
        BasetenNamedCheckpointConfig: {
            checkpoint_name: string;
            job_id?: string
            | null;
            project_name?: string | null;
            typ: "baseten_named_checkpoint";
        };
        BenchmarkSnapshot: {
            embedding?: components["schemas"]["EmbeddingBenchmarkMetrics"]
            | null;
            llm?: components["schemas"]["LLMBenchmarkMetrics"] | null;
            measured_at: string;
            profile?: string | null;
            replicas?: number | null;
            run_id: string;
            tts?: components["schemas"]["TTSBenchmarkMetrics"] | null;
        };
        BillableResource: {
            base_model: string
            | null;
            chain_metadata: components["schemas"]["ChainMetadata"] | null;
            environment_name: string | null;
            id: string;
            instance_type: string | null;
            is_deleted: boolean;
            kind: components["schemas"]["ResourceKind"];
            model_id: string | null;
            model_name: string | null;
            name: string | null;
            team_id: string | null;
            team_name: string | null;
        };
        BucketWidth: "1m"
        | "1h"
        | "1d";
        CancelPromotionResponse: {
            message: string;
            status: components["schemas"]["CancelPromotionStatus"];
        };
        CancelPromotionStatus: "CANCELED"
        | "RAMPING_DOWN";
        CapacityAtSubmit: {
            gpu_type: string;
            last_modified: string;
            max_gpus: number;
            min_gpus: number | null;
        };
        Chain: {
            created_at: string;
            deployments_count: number;
            id: string;
            name: string;
            team_name: string;
        };
        ChainDeployment: {
            chain_id: string;
            chainlets: components["schemas"]["Chainlet"][];
            created_at: string;
            environment: string
            | null;
            id: string;
            status: components["schemas"]["DeploymentStatus"];
        };
        ChainDeployments: {
            deployments: components["schemas"]["ChainDeployment"][];
        };
        ChainDeploymentTombstone: {
            chain_id: string;
            deleted: boolean;
            id: string;
        };
        ChainEnvironment: {
            candidate_deployment: components["schemas"]["ChainDeployment"]
            | null;
            chain_id: string;
            chainlet_settings: components["schemas"]["ChainletEnvironmentSettings"][];
            created_at: string;
            current_deployment: components["schemas"]["ChainDeployment"] | null;
            name: string;
            promotion_settings: components["schemas"]["PromotionSettings"];
        };
        Chainlet: {
            active_replica_count: number;
            autoscaling_settings: components["schemas"]["AutoscalingSettings"]
            | null;
            id: string;
            instance_type_name: string;
            name: string;
            status: components["schemas"]["DeploymentStatus"];
        };
        ChainletEnvironmentAutoscalingSettingsUpdate: {
            autoscaling_settings: components["schemas"]["UpdateAutoscalingSettings"];
            chainlet_name: string;
        };
        ChainletEnvironmentInstanceTypeUpdate: {
            chainlet_name: string;
            instance_type_id: string;
        };
        ChainletEnvironmentSettings: {
            autoscaling_settings: | components["schemas"]["AutoscalingSettings"]
            | null;
            chainlet_name: string;
            instance_type: components["schemas"]["InstanceType"];
        };
        ChainletEnvironmentSettingsRequest: {
            autoscaling_settings?: | components["schemas"]["UpdateAutoscalingSettings"]
            | null;
            chainlet_name: string;
            instance_type_id?: string;
        };
        ChainMetadata: {
            chain_deployment_id: string;
            chain_id: string;
            chain_name: string
            | null;
        };
        Chains: { chains: components["schemas"]["Chain"][] };
        ChainTombstone: { deleted: boolean; id: string };
        CheckpointFile: {
            last_modified: string;
            node_rank: number;
            relative_file_name: string;
            size_bytes: number;
            url: string;
        };
        CheckpointSyncStatus: "SYNCING"
        | "COMPLETED";
        CreateApiKeyForGroupRequest: { name?: string | null };
        CreateApiKeyForGroupResponse: {
            api_key: string;
            name: string | null;
            prefix: string;
        };
        CreateAPIKeyRequest: {
            model_ids?: string[]
            | null;
            name?: string | null;
            team_id?: string | null;
            type: components["schemas"]["APIKeyCategory"];
        };
        CreateChainEnvironmentRequest: {
            chainlet_settings?: | components["schemas"]["ChainletEnvironmentSettingsRequest"][]
            | null;
            name: string;
            promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
            | null;
        };
        CreateDeploymentPatchRequest: {
            next_patch_point: components["schemas"]["DeploymentPatchPoint"];
            patch_ops: (
                | components["schemas"]["DeploymentPatchOpModelCode"]
                | components["schemas"]["DeploymentPatchOpPackage"]
                | components["schemas"]["DeploymentPatchOpConfig"]
                | components["schemas"]["DeploymentPatchOpPythonRequirement"]
                | components["schemas"]["DeploymentPatchOpEnvVar"]
                | components["schemas"]["DeploymentPatchOpExternalData"]
            )[];
            prev_patch_hash: string;
        };
        CreateDeploymentPatchResponse: {
            patch_point: components["schemas"]["DeploymentPatchPointWithHash"];
        };
        CreatedModelDeployment: {
            deployment: components["schemas"]["Deployment"];
            model: components["schemas"]["Model"];
        };
        CreateEndpointRequest: {
            region?: components["schemas"]["SharedEndpointRegion"];
            slug: string;
            targets: components["schemas"]["EndpointTargetRequest"][];
        };
        CreateEnvironmentRequest: {
            autoscaling_settings?: | components["schemas"]["UpdateAutoscalingSettings"]
            | null;
            name: string;
            promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
            | null;
            request_backpressure_settings?: | components["schemas"]["UpdateRequestBackpressureSettings"]
            | null;
        };
        CreateGroupHierarchy: {
            limit_enforcement?: components["schemas"]["LimitEnforcement"]
            | null;
            parent_group_id?: string | null;
        };
        CreateGroupRequest: {
            hierarchy: components["schemas"]["CreateGroupHierarchy"];
            metadata: components["schemas"]["GroupMetadata"];
            models: components["schemas"]["ModelConfig"][];
        };
        CreateJobWeightConfig: {
            allow_patterns?: string[]
            | null;
            auth?: components["schemas"]["TrainingWeightAuth"] | null;
            auth_secret_name?: string | null;
            ignore_patterns?: string[] | null;
            mount_location: string;
            source: string;
        };
        CreateLibraryListingRequest: {
            closed_source?: boolean;
            display_name: string;
            is_public?: boolean;
            user_defined_id: string;
        };
        CreateLibraryListingVersionRequest: {
            allow_truss_download?: boolean;
            closed_source?: boolean;
            display_name?: string
            | null;
            is_public?: boolean;
            oracle_version_id: string;
            version_tag: string;
        };
        CreateLLMModelRequest: {
            additional_autoscaling_config?: { [key: string]: unknown }
            | null;
            autoscaling_settings?:
                | components["schemas"]["UpdateAutoscalingSettings"]
                | null;
            environment_variables?: { [key: string]: unknown };
            llm_config?: { [key: string]: unknown };
            llm_version?: string | null;
            metadata?: { [key: string]: unknown } | null;
            model_metadata?: { [key: string]: unknown } | null;
            name: string;
            region?: string | null;
            resources: { [key: string]: unknown };
            weights?: { [key: string]: unknown }[] | null;
        };
        CreateLLMModelVersionRequest: {
            additional_autoscaling_config?: { [key: string]: unknown }
            | null;
            autoscaling_settings?:
                | components["schemas"]["UpdateAutoscalingSettings"]
                | null;
            environment_variables?: { [key: string]: unknown };
            llm_config?: { [key: string]: unknown };
            llm_version?: string | null;
            metadata?: { [key: string]: unknown } | null;
            model_metadata?: { [key: string]: unknown } | null;
            region?: string | null;
            resources: { [key: string]: unknown };
            weights?: { [key: string]: unknown }[] | null;
        };
        CreateLoopsRunRequest: {
            availability_model?: components["schemas"]["V1AvailabilityModel"];
            base_model: string;
            lora_rank?: number;
            max_seq_len?: number
            | null;
            name?: string | null;
            path?: string | null;
            replicas?: number;
            reuse_from_run_id?: string | null;
            reuse_from_session_id?: string | null;
            scale_down_delay_seconds?: number;
            seed?: number | null;
            session_id: string;
        };
        CreateLoopsRunResponse: { run: components["schemas"]["LoopsRun"] };
        CreateLoopsSamplerRequest: {
            base_model?: string | null;
            max_seq_length?: number | null;
            model_path?: string | null;
            reuse_from_session_id?: string | null;
            run_id?: string | null;
            session_id: string;
        };
        CreateLoopsSamplerResponse: {
            sampler: components["schemas"]["LoopsSampler"];
        };
        CreateLoopsSessionResponse: {
            session: components["schemas"]["LoopsSession"];
        };
        CreateModelDeploymentRequest: {
            source: components["schemas"]["DeploymentArchiveSource"];
        };
        CreateModelRequest: {
            source: | components["schemas"]["LibraryListingSource"]
            | components["schemas"]["ModelArchiveSource"];
        };
        CreateTrainingJob: {
            compute?: components["schemas"]["CreateTrainingJobCompute"];
            enable_baseten_workdir?: boolean;
            image: components["schemas"]["CreateTrainingJobImage"];
            interactive_session?: | components["schemas"]["InteractiveSessionConfig"]
            | null;
            name?: string
            | null;
            priority?: number | null;
            runtime?: components["schemas"]["CreateTrainingJobRuntime"];
            truss_user_env?: components["schemas"]["TrussUserEnv"] | null;
            weights?: components["schemas"]["CreateJobWeightConfig"][];
        };
        CreateTrainingJobAccelerator: { accelerator: string; count: number };
        CreateTrainingJobCacheConfig: {
            enable_legacy_hf_mount?: boolean;
            enabled?: boolean;
            mount_base_path?: string;
            require_cache_affinity?: boolean;
        };
        CreateTrainingJobCheckpointingConfig: {
            checkpoint_path?: string
            | null;
            enabled?: boolean;
            volume_size_gib?: number | null;
        };
        CreateTrainingJobCompute: {
            accelerator?: | components["schemas"]["CreateTrainingJobAccelerator"]
            | null;
            availability_model?: components["schemas"]["V1AvailabilityModel"];
            cpu_count?: number;
            memory?: string;
            node_count?: number;
        };
        CreateTrainingJobImage: {
            base_image: string;
            docker_auth?: components["schemas"]["DockerAuth"]
            | null;
        };
        CreateTrainingJobRequest: {
            training_job: components["schemas"]["CreateTrainingJob"];
        };
        CreateTrainingJobResponse: {
            training_job: components["schemas"]["TrainingJob"];
        };
        CreateTrainingJobRuntime: {
            artifacts?: components["schemas"]["CreateTrainingJobS3Artifact"][];
            cache_config?: | components["schemas"]["CreateTrainingJobCacheConfig"]
            | null;
            checkpointing_config?: components["schemas"]["CreateTrainingJobCheckpointingConfig"];
            enable_cache?: boolean
            | null;
            environment_variables?: { [key: string]: string | { name: string } };
            load_checkpoint_config?:
                | components["schemas"]["LoadCheckpointConfig"]
                | null;
            start_commands?: string[];
        };
        CreateTrainingJobS3Artifact: { s3_bucket: string; s3_key: string };
        CreateVolumeTokenRequest: {
            correlation_id?: string | null;
            namespaces: string[];
            scopes: components["schemas"]["VolumeTokenScope"][];
            volumes: string[];
        };
        CreateVolumeTokenResponse: {
            bdn_endpoint: string
            | null;
            expires_at: string;
            namespaces: string[];
            scopes: components["schemas"]["VolumeTokenScope"][];
            token: string;
            volumes: string[];
        };
        DailyDedicatedUsage: {
            compute_cost: number
            | string;
            date: string;
            inference_requests: number;
            minutes: number;
            subtotal: number | string;
            surcharge_cost: number | string;
        };
        DailyModelApiUsage: {
            cached_input_tokens: number;
            date: string;
            input_tokens: number;
            output_tokens: number;
            subtotal: number
            | string;
        };
        DailyTrainingUsage: {
            date: string;
            minutes: number;
            subtotal: number
            | string;
        };
        DeactivateLoopsDeploymentResponse: {
            base_model: string;
            id: string;
            user: components["schemas"]["User"];
        };
        DeactivateLoopsRunResponse: {
            base_model: string;
            id: string;
            user: components["schemas"]["User"];
        };
        DeactivateResponse: { no_op: boolean; success: boolean };
        DedicatedItem: {
            billable_resource: components["schemas"]["BillableResource"];
            compute_cost: number | string;
            daily?: components["schemas"]["DailyDedicatedUsage"][];
            inference_requests: number;
            minutes: number;
            subtotal: number | string;
            surcharge_cost: number | string;
        };
        DedicatedUsage: {
            breakdown?: components["schemas"]["DedicatedItem"][];
            credits_used: number
            | string;
            minutes: number;
            subtotal: number | string;
            total: number | string;
        };
        DeleteVolumeRequest: { expected_sequence?: number
        | null };
        DeleteVolumeResponse: {
            name: string;
            namespace: string;
            versions_deleted: number;
            volume_sequence: number;
        };
        DeleteVolumeVersionRequest: { expected_sequence?: number
        | null };
        DeleteVolumeVersionResponse: {
            delete_after: string;
            digest: string;
            lifecycle: string;
            namespace: string;
            version_ref: string;
            volume: string;
            volume_sequence: number;
        };
        Deployment: {
            active_replica_count: number;
            autoscaling_settings: components["schemas"]["AutoscalingSettings"]
            | null;
            created_at: string;
            environment: string | null;
            id: string;
            instance_type_name: string | null;
            is_development: boolean;
            is_production: boolean;
            labels: { [key: string]: unknown } | null;
            model_id: string;
            name: string;
            region: components["schemas"]["Region"] | null;
            request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"];
            status: components["schemas"]["DeploymentStatus"];
        };
        DeploymentArchivePayload: {
            config: { [key: string]: unknown };
            create_environment_if_missing?: boolean;
            deploy_timeout_minutes?: number | null;
            deployment_name?: string | null;
            environment_name?: string | null;
            is_development?: boolean;
            labels?: { [key: string]: unknown } | null;
            preserve_env_instance_type?: boolean;
            raw_config?: string | null;
            region?: string | null;
            user_env?: { [key: string]: unknown } | null;
        };
        DeploymentArchiveSource: {
            deployment: components["schemas"]["DeploymentArchivePayload"];
            kind: "model_archive";
            s3_key?: string
            | null;
        };
        DeploymentConfigOutputFormat: "raw"
        | "parsed"
        | "both";
        DeploymentConfigResponse: {
            config: { [key: string]: unknown } | null;
            raw_config: string | null;
        };
        DeploymentPatchAction: "ADD"
        | "UPDATE"
        | "REMOVE";
        DeploymentPatchOpConfig: {
            config: { [key: string]: unknown };
            path?: string;
            type: "config";
        };
        DeploymentPatchOpEnvVar: {
            action: components["schemas"]["DeploymentPatchAction"];
            name: string;
            type: "environment_variable";
            value?: string
            | null;
        };
        DeploymentPatchOpExternalData: {
            action: components["schemas"]["DeploymentPatchAction"];
            item: { [key: string]: string };
            type: "external_data";
        };
        DeploymentPatchOpModelCode: {
            action: components["schemas"]["DeploymentPatchAction"];
            content?: string
            | null;
            content_bytes?: string | null;
            hot_reload?: boolean;
            path: string;
            type: "model_code";
        };
        DeploymentPatchOpPackage: {
            action: components["schemas"]["DeploymentPatchAction"];
            content?: string
            | null;
            content_bytes?: string | null;
            path: string;
            type: "package";
        };
        DeploymentPatchOpPythonRequirement: {
            action: components["schemas"]["DeploymentPatchAction"];
            requirement: string;
            type: "python_requirement";
        };
        DeploymentPatchPoint: {
            config: string;
            content_hashes: { [key: string]: string
            | null };
            requirements?: string[];
        };
        DeploymentPatchPointWithHash: {
            config: string;
            content_hashes: { [key: string]: string
            | null };
            hash: string;
            requirements?: string[];
        };
        Deployments: { deployments: components["schemas"]["Deployment"][] };
        DeploymentStatus:
            | "BUILDING"
            | "DEPLOYING"
            | "DEPLOY_FAILED"
            | "LOADING_MODEL"
            | "ACTIVE"
            | "UNHEALTHY"
            | "BUILD_FAILED"
            | "BUILD_STOPPED"
            | "DEACTIVATING"
            | "INACTIVE"
            | "FAILED"
            | "UPDATING"
            | "SCALED_TO_ZERO"
            | "WAKING_UP";
        DeploymentTombstone: { deleted: boolean; id: string; model_id: string };
        DockerAuth: {
            auth_method: components["schemas"]["DockerAuthType"];
            aws_assume_role_docker_auth?:
                | components["schemas"]["AwsAssumeRoleDockerAuth"]
                | null;
            aws_iam_docker_auth?: components["schemas"]["AwsIamDockerAuth"]
            | null;
            aws_oidc_docker_auth?: components["schemas"]["AwsOidcDockerAuth"] | null;
            gcp_oidc_docker_auth?: components["schemas"]["GcpOidcDockerAuth"] | null;
            gcp_service_account_json_docker_auth?:
                | components["schemas"]["GcpServiceAccountJsonDockerAuth"]
                | null;
            registry: string;
            registry_secret_docker_auth?: | components["schemas"]["RegistrySecretDockerAuth"]
            | null;
        };
        DockerAuthType: | "GCP_SERVICE_ACCOUNT_JSON"
        | "AWS_IAM"
        | "AWS_OIDC"
        | "GCP_OIDC"
        | "REGISTRY_SECRET"
        | "AWS_ASSUME_ROLE";
        DownloadDeploymentResponse: { download_url: string };
        DownloadTrainingJobResponse: { artifact_presigned_urls: string[] };
        EffectiveModelConfig: {
            rate_limits?: components["schemas"]["EffectiveRateLimit"][];
            slug: string;
            usage_limits?: components["schemas"]["EffectiveUsageLimit"][];
        };
        EffectiveRateLimit: {
            source_group: string;
            threshold: number;
            type: components["schemas"]["LimitType"];
            unit: components["schemas"]["RateLimitUnit"];
        };
        EffectiveUsageLimit: {
            source_group: string;
            threshold: number;
            type: components["schemas"]["LimitType"];
            unit: components["schemas"]["UsageLimitUnit"];
        };
        EmbeddingBenchmarkMetrics: {
            e2e_latency_ms_p50?: number
            | null;
            e2e_latency_ms_p99?: number | null;
            input_tokens_per_sec?: number | null;
            requests_per_sec?: number | null;
        };
        Endpoint: {
            created_at: string;
            id: string;
            region: components["schemas"]["SharedEndpointRegion"];
            slug: string;
            targets: components["schemas"]["EndpointTarget"][];
            updated_at: string;
        };
        EndpointsResponse: {
            items: components["schemas"]["Endpoint"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        EndpointTarget: {
            base_url: string
            | null;
            environment_name: string | null;
            model_id: string | null;
            provider: components["schemas"]["GatewayProvider"];
            secret_id: string | null;
            target_model: string | null;
            vertex_config: components["schemas"]["VertexTargetConfig"] | null;
        };
        EndpointTargetRequest: {
            base_url?: string
            | null;
            environment_name?: string | null;
            model_id?: string | null;
            provider: components["schemas"]["GatewayProvider"];
            secret_id?: string | null;
            target_model?: string | null;
            vertex_config?: components["schemas"]["VertexTargetConfig"] | null;
        };
        EndpointTombstone: { id: string; slug: string };
        Environment: {
            autoscaling_schedules:
                | components["schemas"]["EnvironmentAutoscalingSchedules"]
                | null;
            autoscaling_settings: components["schemas"]["AutoscalingSettings"];
            candidate_deployment: components["schemas"]["Deployment"]
            | null;
            created_at: string;
            current_deployment: components["schemas"]["Deployment"] | null;
            in_progress_promotion: components["schemas"]["InProgressPromotion"] | null;
            instance_type: components["schemas"]["InstanceType"];
            model_id: string;
            name: string;
            promotion_settings: components["schemas"]["PromotionSettings"];
            request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"];
        };
        EnvironmentAutoscalingSchedules: {
            applied_state: components["schemas"]["AutoscalingScheduleState"]
            | null;
            schedules: (
                | components["schemas"]["AutoscalingSchedule"]
                | components["schemas"]["OneTimeAutoscalingSchedule"]
            )[];
            timezone: string
            | null;
        };
        EnvironmentGroup: {
            manage_access: components["schemas"]["EnvironmentGroupManageAccess"];
            name: string;
            team_id: string;
            team_name: string;
        };
        EnvironmentGroupManageAccess: {
            is_restricted: boolean;
            users?: components["schemas"]["EnvironmentGroupUser"][];
        };
        EnvironmentGroups: {
            items: components["schemas"]["EnvironmentGroup"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        EnvironmentGroupUser: {
            email: string
            | null;
            name: string | null;
            user_id: string;
        };
        Environments: { environments: components["schemas"]["Environment"][] };
        EnvironmentTombstone: { deleted: boolean; model_id: string; name: string };
        FileSummary: {
            file_type: string;
            modified: string;
            path: string;
            permissions: string;
            size_bytes: number;
        };
        GatewayEvent: {
            apiKeyPrefix: string;
            externalEntityId: string;
            idempotencyKey: string;
            modelSlug: string;
            requestId: string;
            timestamp: string;
            tokens: components["schemas"]["GatewayEventTokens"];
            type: string;
        };
        GatewayEventsResponse: {
            items: components["schemas"]["GatewayEvent"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        GatewayEventTokens: {
            cachedInputTokens: number;
            inputTokens: number;
            outputTokens: number;
        };
        GatewayKeyInfo: { name: string
        | null; prefix: string };
        GatewayProvider:
            | "ANTHROPIC"
            | "OPENAI"
            | "XAI"
            | "BASETEN"
            | "BASETEN_MODEL_API"
            | "VERTEX"
            | "OPENAI_COMPATIBLE";
        GcpOidcDockerAuth: {
            service_account: string;
            workload_identity_provider: string;
        };
        GcpServiceAccountJsonDockerAuth: {
            service_account_json_secret_ref: components["schemas"]["SecretReference"];
        };
        GetAuditLogsRequest: {
            chain_deployment_ids?: string[];
            cursor?: string
            | null;
            deployment_ids?: string[];
            direction?: components["schemas"]["AuditLogSortDirection"];
            end_epoch_millis?: number | null;
            environment_names?: string[];
            event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
            limit?: number;
            search?: string | null;
            sources?: components["schemas"]["AuditLogSource"][];
            start_epoch_millis?: number | null;
            user_ids?: string[];
        };
        GetAuthCodesResponse: { auth_codes: components["schemas"]["AuthCode"][] };
        GetBillingModelApisRequest: {
            api_key_prefixes?: string[];
            cursor?: string | null;
            end_date?: string | null;
            group_by?: components["schemas"]["ModelApiCostDimension"][];
            limit?: number;
            models?: string[];
            service_tiers?: string[];
            start_date?: string | null;
            user_ids?: string[];
        };
        GetBillingUsageSummaryRequest: { end_date: string; start_date: string };
        GetBlobCredentialsResponse: {
            creds: components["schemas"]["AWSCredentials"];
            s3_bucket: string;
            s3_key: string;
        };
        GetCacheSummaryResponse: {
            file_summaries: components["schemas"]["FileSummary"][];
            project_id: string;
            timestamp: string;
        };
        GetChainsAuditLogsRequest: {
            chain_deployment_ids?: string[];
            cursor?: string
            | null;
            deployment_ids?: string[];
            direction?: components["schemas"]["AuditLogSortDirection"];
            end_epoch_millis?: number | null;
            environment_names?: string[];
            event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
            limit?: number;
            search?: string | null;
            sources?: components["schemas"]["AuditLogSource"][];
            start_epoch_millis?: number | null;
            user_ids?: string[];
        };
        GetChainsDeploymentsChainletsLogsRequest: {
            component?: string
            | null;
            direction?: components["schemas"]["SortOrder"] | null;
            end_epoch_millis?: number | null;
            excludes?: string[];
            includes?: string[];
            limit?: number | null;
            min_level?: components["schemas"]["LogLevel"] | null;
            replica?: string | null;
            request_id?: string | null;
            search_pattern?: string | null;
            start_epoch_millis?: number | null;
        };
        GetDeploymentLogsRequest: {
            component?: string
            | null;
            direction?: components["schemas"]["SortOrder"] | null;
            end_epoch_millis?: number | null;
            excludes?: string[];
            includes?: string[];
            limit?: number | null;
            min_level?: components["schemas"]["LogLevel"] | null;
            replica?: string | null;
            request_id?: string | null;
            search_pattern?: string | null;
            start_epoch_millis?: number | null;
        };
        GetDeploymentPatchesStateResponse: {
            pending_patch_point: | components["schemas"]["DeploymentPatchPointWithHash"]
            | null;
            running_patch_point: components["schemas"]["DeploymentPatchPointWithHash"];
        };
        GetGatewayEventsRequest: {
            api_keys?: string[];
            cursor?: string
            | null;
            end_time?: string | null;
            external_entity_ids?: string[];
            limit?: number | null;
            start_time?: string | null;
        };
        GetLogsResponse: { logs: components["schemas"]["Log"][] };
        GetLoopsCapabilitiesResponse: {
            supported_models: components["schemas"]["SupportedModel"][];
        };
        GetLoopsCheckpointsFilesRequest: {
            page_size?: number;
            page_token?: number;
        };
        GetLoopsCheckpointsRequest: {
            base_model?: string
            | null;
            checkpoint_path?: string | null;
            run_id?: string | null;
        };
        GetLoopsDeploymentMetricsRequest: {
            end_epoch_millis?: number
            | null;
            start_epoch_millis?: number | null;
            step_seconds?: number | null;
            time_divisor_seconds?: number | null;
        };
        GetLoopsDeploymentMetricsResponse: {
            deployment_id: string;
            metrics: components["schemas"]["LoopsDeploymentMetrics"];
        };
        GetLoopsDeploymentResponse: {
            deployment: components["schemas"]["LoopsDeployment"];
        };
        GetLoopsDeploymentsDebugArchiveFilesRequest: {
            page_size?: number;
            page_token?: string
            | null;
        };
        GetLoopsDeploymentsLogsRequest: {
            direction?: components["schemas"]["SortOrder"]
            | null;
            end_epoch_millis?: number | null;
            limit?: number | null;
            min_level?: components["schemas"]["LogLevel"] | null;
            start_epoch_millis?: number | null;
        };
        GetLoopsDeploymentsRequest: { scope?: string
        | null };
        GetLoopsRunResponse: { run: components["schemas"]["LoopsRun"] };
        GetLoopsRunsRequest: {
            base_model?: string | null;
            run_id?: string | null;
            scope?: string | null;
        };
        GetLoopsSamplerResponse: { sampler: components["schemas"]["LoopsSampler"] };
        GetLoopsSamplersRequest: { scope?: string | null };
        GetLoopsSessionResponse: { session: components["schemas"]["LoopsSession"] };
        GetLoopsUserConfigResponse: {
            user_config: components["schemas"]["LoopsUserConfig"];
        };
        GetModelApisRequest: {
            added_only?: boolean;
            cursor?: string
            | null;
            limit?: number;
        };
        GetModelApisUsageRequest: {
            api_keys?: string[];
            bucket_width?: components["schemas"]["BucketWidth"];
            cursor?: string
            | null;
            end_time?: string | null;
            group_by?: components["schemas"]["UsageDimension"][];
            limit?: number | null;
            models?: string[];
            start_time?: string | null;
            user_ids?: string[];
        };
        GetModelMetricsResponse: {
            end_epoch_millis: number;
            metric_descriptors: components["schemas"]["ModelMetricDescriptor"][];
            metric_values: components["schemas"]["ModelMetricValueSet"][];
            mode: components["schemas"]["ModelMetricMode"];
            start_epoch_millis: number;
            step_seconds: number
            | null;
        };
        GetModelsAuditLogsRequest: {
            chain_deployment_ids?: string[];
            cursor?: string
            | null;
            deployment_ids?: string[];
            direction?: components["schemas"]["AuditLogSortDirection"];
            end_epoch_millis?: number | null;
            environment_names?: string[];
            event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
            limit?: number;
            search?: string | null;
            sources?: components["schemas"]["AuditLogSource"][];
            start_epoch_millis?: number | null;
            user_ids?: string[];
        };
        GetModelsDeploymentsConfigRequest: {
            output_format?: components["schemas"]["DeploymentConfigOutputFormat"];
        };
        GetModelsDeploymentsLogsRequest: {
            component?: string
            | null;
            direction?: components["schemas"]["SortOrder"] | null;
            end_epoch_millis?: number | null;
            excludes?: string[];
            includes?: string[];
            limit?: number | null;
            min_level?: components["schemas"]["LogLevel"] | null;
            replica?: string | null;
            request_id?: string | null;
            search_pattern?: string | null;
            start_epoch_millis?: number | null;
        };
        GetModelsDeploymentsMetricsRequest: {
            end_epoch_millis?: number
            | null;
            metrics?: string[];
            mode?: components["schemas"]["ModelMetricMode"];
            start_epoch_millis?: number | null;
        };
        GetModelsDeploymentsRequest: { name?: string
        | null };
        GetModelsEnvironmentsLogsRequest: {
            component?: string | null;
            direction?: components["schemas"]["SortOrder"] | null;
            end_epoch_millis?: number | null;
            excludes?: string[];
            includes?: string[];
            limit?: number | null;
            min_level?: components["schemas"]["LogLevel"] | null;
            replica?: string | null;
            request_id?: string | null;
            search_pattern?: string | null;
            start_epoch_millis?: number | null;
        };
        GetModelsEnvironmentsMetricsRequest: {
            end_epoch_millis?: number
            | null;
            metrics?: string[];
            mode?: components["schemas"]["ModelMetricMode"];
            start_epoch_millis?: number | null;
        };
        GetModelsRequest: { name?: string
        | null };
        GetTeamsLoopsRunsRequest: {
            base_model?: string | null;
            run_id?: string | null;
            scope?: string | null;
        };
        GetTeamsLoopsSamplersRequest: { scope?: string
        | null };
        GetTeamsModelsRequest: { name?: string | null };
        GetTeamsRequest: { name?: string | null };
        GetTrainingGpuCapacityResponse: {
            gpu_capacities: components["schemas"]["TrainingGpuCapacityItem"][];
            team_gpu_capacities?: components["schemas"]["TeamTrainingGpuCapacityItem"][];
        };
        GetTrainingJobCheckpointFilesResponse: {
            next_page_token: number
            | null;
            presigned_urls: components["schemas"]["CheckpointFile"][];
            total_count: number;
        };
        GetTrainingJobCheckpointsResponse: {
            checkpoints: components["schemas"]["TrainingJobCheckpoint"][];
            training_job: components["schemas"]["TrainingJob"];
        };
        GetTrainingJobLogsRequest: {
            direction?: components["schemas"]["SortOrder"]
            | null;
            end_epoch_millis?: number | null;
            limit?: number | null;
            min_level?: components["schemas"]["LogLevel"] | null;
            start_epoch_millis?: number | null;
        };
        GetTrainingJobMetricsRequest: {
            end_epoch_millis?: number
            | null;
            start_epoch_millis?: number | null;
            step_seconds?: number | null;
        };
        GetTrainingJobMetricsResponse: {
            cache: components["schemas"]["StorageMetrics"]
            | null;
            cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
            cpu_usage: components["schemas"]["TrainingJobMetric"][];
            ephemeral_storage: components["schemas"]["StorageMetrics"];
            gpu_memory_usage_bytes: {
                [key: string]: { timestamp: string; value: number }[];
            };
            gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
            per_node_metrics: components["schemas"]["TrainingJobNodeMetrics"][];
            training_job: components["schemas"]["TrainingJob"];
        };
        GetTrainingJobQueueContextResponse: {
            active_at_submit: components["schemas"]["ActiveJobAtSubmit"][];
            events: components["schemas"]["QueueEvent"][];
            events_window_end: string;
            gpu_type: string;
            org_capacity: components["schemas"]["CapacityAtSubmit"]
            | null;
            pending_ahead_at_submit: components["schemas"]["PendingJobAheadAtSubmit"][];
            pending_seconds: number | null;
            released_at: string | null;
            requested_gpus: number;
            submitted_at: string;
            target_job_id: string;
            target_job_name: string | null;
            team_capacity: components["schemas"]["CapacityAtSubmit"] | null;
        };
        GetTrainingJobResponse: {
            training_job: components["schemas"]["TrainingJob"];
            training_project: components["schemas"]["TrainingProject"];
        };
        GetTrainingProjectResponse: {
            training_project: components["schemas"]["TrainingProject"];
        };
        GetTrainingProjectsJobsCheckpointFilesRequest: {
            page_size?: number;
            page_token?: number;
        };
        GetTrainingProjectsJobsLogsRequest: {
            direction?: components["schemas"]["SortOrder"]
            | null;
            end_epoch_millis?: number | null;
            limit?: number | null;
            min_level?: components["schemas"]["LogLevel"] | null;
            start_epoch_millis?: number | null;
        };
        GetTrainingProjectsJobsMetricsRequest: {
            end_epoch_millis?: number
            | null;
            start_epoch_millis?: number | null;
            step_seconds?: number | null;
        };
        GetUsersRequest: {
            cursor?: string
            | null;
            email?: string | null;
            limit?: number;
        };
        GetVolumesNamespacesRequest: { cursor?: string
        | null; limit?: number };
        GetVolumesRequest: {
            cursor?: string | null;
            limit?: number;
            namespace: string;
        };
        GetVolumesVersionsRequest: { include_tombstoned?: boolean };
        GitInfo: {
            commits_since_tag: number | null;
            has_uncommitted_changes: boolean;
            latest_commit_sha: string;
            latest_tag: string | null;
        };
        Group: {
            created_at: string;
            effective_models?: components["schemas"]["EffectiveModelConfig"][];
            hierarchy: components["schemas"]["GroupHierarchy"];
            id: string;
            metadata: components["schemas"]["GroupMetadata"];
            models?: components["schemas"]["ModelConfig"][];
        };
        GroupHierarchy: {
            limit_enforcement: components["schemas"]["LimitEnforcement"];
            parent_group_id: string
            | null;
        };
        GroupMetadata: { external_entity_id: string; name?: string
        | null };
        GroupsResponse: {
            items: components["schemas"]["Group"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        InferenceVolumeByStatusDatapoint: {
            status_2xx: number;
            status_4xx: number;
            status_5xx: number;
            timestamp: string;
        };
        InProgressPromotion: {
            error_message: string
            | null;
            percent_traffic_to_new_version: number;
            rolling_deploy: boolean | null;
            status: components["schemas"]["InProgressPromotionStatus"];
        };
        InProgressPromotionStatus: | "RELEASING"
        | "RAMPING_UP"
        | "RAMPING_DOWN"
        | "PAUSED"
        | "SUCCEEDED"
        | "FAILED"
        | "CANCELED";
        InstanceType: {
            gpu_count: number;
            gpu_memory_limit_mib: number
            | null;
            gpu_type: string | null;
            id: string;
            memory_limit_mib: number;
            millicpu_limit: number;
            name: string;
        };
        InstanceTypePrices: {
            instance_types: components["schemas"]["InstanceTypeWithPrice"][];
        };
        InstanceTypes: { instance_types: components["schemas"]["InstanceType"][] };
        InstanceTypeWithPrice: {
            instance_type: components["schemas"]["InstanceType"];
            price: number;
        };
        InteractiveSession: {
            auth_code: string
            | null;
            auth_code_generated_at: string | null;
            auth_provider: string;
            auth_url: string | null;
            authenticated_at: string | null;
            expires_at: string | null;
            id: string;
            pod_name: string;
            session_provider: string;
            timeout_minutes: number;
            trigger: string;
            tunnel_name: string | null;
            working_directory: string | null;
        };
        InteractiveSessionConfig: {
            auth_provider?: components["schemas"]["V1InteractiveSessionAuthProvider"];
            session_provider?: components["schemas"]["V1InteractiveSessionProvider"];
            timeout_minutes?: number;
            trigger?: components["schemas"]["V1InteractiveSessionTrigger"];
        };
        KeysForGroupResponse: {
            items: components["schemas"]["GatewayKeyInfo"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        LibraryListing: {
            closed_source: boolean;
            created_at: string;
            display_name: string;
            is_public: boolean;
            metadata: components["schemas"]["LibraryListingMetadata"]
            | null;
            modified_at: string;
            trending: boolean | null;
            user_defined_id: string;
        };
        LibraryListingMetadata: {
            context_length?: number
            | null;
            description?: string | null;
            input_modalities?: components["schemas"]["LibraryListingModality"][];
            license: string;
            model_api_slug?: string | null;
            output_modalities?: components["schemas"]["LibraryListingModality"][];
            parameter_count?: number | null;
            publisher?: string | null;
            release_date?: string | null;
            trending?: boolean;
            variant?: string | null;
        };
        LibraryListingModality: | "text"
        | "image"
        | "audio"
        | "video"
        | "embedding"
        | "rerank";
        LibraryListings: { listings: components["schemas"]["LibraryListing"][] };
        LibraryListingSource: {
            deployed_model_name?: string | null;
            kind: "library_listing";
            lab_display_name: string;
            user_defined_listing_id: string;
        };
        LibraryListingTombstone: { deleted: boolean; user_defined_id: string };
        LibraryListingVersion: {
            allow_truss_download: boolean;
            benchmark: components["schemas"]["BenchmarkSnapshot"] | null;
            created_at: string;
            is_live: boolean;
            modified_at: string;
            oracle_version_id: string;
            version_tag: string;
        };
        LibraryListingVersions: {
            versions: components["schemas"]["LibraryListingVersion"][];
        };
        LibraryListingVersionTombstone: { deleted: boolean; version_tag: string };
        LimitEnforcement: "CASCADING" | "INDEPENDENT";
        LimitType:
            | "REQUEST"
            | "TOKEN"
            | "CONCURRENT_REQUEST"
            | "UNCACHED_INPUT_TOKEN"
            | "OUTPUT_TOKEN";
        ListAuditLogsResponse: {
            items: components["schemas"]["AuditLogEntry"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        ListLoopsCheckpointsResponse: {
            checkpoints: components["schemas"]["LoopsCheckpoint"][];
        };
        ListLoopsDeploymentsResponse: {
            deployments: components["schemas"]["LoopsDeployment"][];
        };
        ListLoopsRunsResponse: { runs: components["schemas"]["LoopsRun"][] };
        ListLoopsSamplersResponse: {
            samplers: components["schemas"]["LoopsSampler"][];
        };
        ListTrainingJobsResponse: {
            training_jobs: components["schemas"]["TrainingJob"][];
            training_project: components["schemas"]["TrainingProject"];
        };
        ListTrainingProjectsResponse: {
            training_projects: components["schemas"]["TrainingProject"][];
        };
        ListVolumeNamespacesResponse: {
            items: string[];
            pagination: components["schemas"]["PaginationResponse"];
        };
        ListVolumesResponse: {
            items: components["schemas"]["Volume"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        ListVolumeVersionsResponse: {
            versions: components["schemas"]["VolumeVersion"][];
            volume_sequence: number;
        };
        LLMBenchmarkMetrics: {
            cost_per_1m_tokens_usd?: number
            | null;
            max_concurrent_users_at_50ms_tpot?: number | null;
            output_tokens_per_sec_per_user_p50?: number | null;
            requests_per_sec_p50?: number | null;
            ttft_ms_p50?: number | null;
        };
        LLMModelHandle: {
            hostname: string;
            instance_type_name: string
            | null;
            model_id: string;
            version_id: string;
        };
        LoadCheckpointConfig: {
            checkpoints?: (
                | components["schemas"]["BasetenLatestCheckpointConfig"]
                | components["schemas"]["BasetenNamedCheckpointConfig"]
                | components["schemas"]["LoopsCheckpointConfig"]
            )[];
            download_folder?: string;
            enabled?: boolean;
        };
        Log: {
            level: components["schemas"]["LogLevel"]
            | null;
            message: string;
            replica: string | null;
            request_id: string | null;
            timestamp: string;
        };
        LogLevel: "DEBUG"
        | "INFO"
        | "WARNING"
        | "ERROR";
        LoopsCheckpoint: {
            base_model: string | null;
            checkpoint_id: string;
            checkpoint_type: string;
            created_at: string;
            id: string;
            lora_adapter_config: { [key: string]: unknown } | null;
            run_id: string;
            size_bytes: number;
            sync_status: string | null;
            target: components["schemas"]["TrainerCheckpointTarget"];
        };
        LoopsCheckpointConfig: {
            checkpoint_name: string;
            run_id: string;
            target?: "trainer"
            | "sampler";
            typ: "loops_checkpoint";
        };
        LoopsCheckpointFilesResponse: {
            next_page_token: number
            | null;
            presigned_urls: components["schemas"]["CheckpointFile"][];
            total_count: number;
        };
        LoopsDebugArchiveFilesResponse: {
            next_page_token: string
            | null;
            presigned_urls: components["schemas"]["CheckpointFile"][];
        };
        LoopsDeployment: {
            active_run_id: string
            | null;
            availability_model: components["schemas"]["V1AvailabilityModel"];
            base_model: string;
            base_url: string;
            created_at: string;
            id: string;
            instance_type: components["schemas"]["InstanceType"];
            latest_run_id: string | null;
            node_count: number;
            sampler: components["schemas"]["LoopsSampler"] | null;
            status: components["schemas"]["LoopsDeploymentStatus"];
            user: components["schemas"]["User"];
        };
        LoopsDeploymentMetrics: {
            concurrent_requests: components["schemas"]["TrainingJobMetric"][];
            cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
            cpu_usage: components["schemas"]["TrainingJobMetric"][];
            ephemeral_storage: components["schemas"]["StorageMetrics"];
            gpu_memory_usage_bytes: {
                [key: string]: { timestamp: string; value: number }[];
            };
            gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
            inference_volume: components["schemas"]["TrainingJobMetric"][];
            inference_volume_by_status: components["schemas"]["InferenceVolumeByStatusDatapoint"][];
            per_node_metrics: components["schemas"]["LoopsDeploymentNodeMetrics"][];
            response_time_stats: components["schemas"]["ResponseTimeDatapoint"][];
        };
        LoopsDeploymentNodeMetrics: {
            cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
            cpu_usage: components["schemas"]["TrainingJobMetric"][];
            ephemeral_storage: components["schemas"]["StorageMetrics"];
            gpu_memory_usage_bytes: {
                [key: string]: { timestamp: string; value: number }[];
            };
            gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
            node_id: string;
        };
        LoopsDeploymentStatus: { name: components["schemas"]["Name"] };
        LoopsRun: {
            base_model: string;
            base_url: string;
            created_at: string;
            deployment_id: string | null;
            id: string;
            name: string;
            sampler: components["schemas"]["LoopsSampler"] | null;
            session_id: string;
            status: components["schemas"]["LoopsRunStatus"];
            user: components["schemas"]["User"];
        };
        LoopsRunStatus: { name: components["schemas"]["LoopsRunStatusName"] };
        LoopsRunStatusName: "ACTIVE" | "INACTIVE";
        LoopsSampler: {
            base_model: string;
            base_url: string;
            created_at: string;
            deployment_id: string;
            id: string;
            instance_type: components["schemas"]["InstanceType"] | null;
            model_id: string;
            node_count: number;
            status: components["schemas"]["LoopsSamplerStatus"];
            user: components["schemas"]["User"];
        };
        LoopsSamplerStatus: { name: components["schemas"]["DeploymentStatus"] };
        LoopsSession: { id: string };
        LoopsUserConfig: {
            sampler_accelerator_priority: string[] | null;
            trainer_accelerator_priority: string[] | null;
        };
        Model: {
            created_at: string;
            deployments_count: number;
            development_deployment_id: string
            | null;
            id: string;
            instance_type_name: string;
            name: string;
            production_deployment_id: string | null;
            team_name: string;
        };
        ModelAPI: {
            context_length: number;
            cost_per_million_input_tokens: number
            | string
            | null;
            cost_per_million_output_tokens: number | string | null;
            description: string;
            display_name: string;
            invoke_url: string;
            model_family: string | null;
            name: string;
            org_details: components["schemas"]["ModelAPIOrgDetails"] | null;
            rate_limits: components["schemas"]["RateLimit"][];
            release_date: string;
        };
        ModelApiCostDimension: "api_key_prefix"
        | "user"
        | "model"
        | "service_tier";
        ModelApiItem: {
            cached_input_tokens: number;
            daily?: components["schemas"]["DailyModelApiUsage"][];
            input_tokens: number;
            model_family: string | null;
            model_name: string;
            output_tokens: number;
            subtotal: number | string;
        };
        ModelAPIOrgDetails: { added_at: string; last_used_at: string
        | null };
        ModelApisCostBucket: {
            date: string;
            results?: components["schemas"]["ModelApisCostResult"][];
        };
        ModelApisCostResult: {
            api_key_prefixes: string[]
            | null;
            model: string | null;
            service_tier: string | null;
            subtotal: string;
            user_id: string | null;
        };
        ModelApisCostsResponse: {
            items: components["schemas"]["ModelApisCostBucket"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        ModelAPIsResponse: {
            items: components["schemas"]["ModelAPI"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        ModelApisUsage: {
            breakdown?: components["schemas"]["ModelApiItem"][];
            credits_used: number
            | string;
            subtotal: number | string;
            total: number | string;
        };
        ModelApisUsageBucket: {
            end_time: string;
            results?: components["schemas"]["ModelApisUsageResult"][];
            start_time: string;
        };
        ModelApisUsageResponse: {
            items: components["schemas"]["ModelApisUsageBucket"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        ModelApisUsageResult: {
            api_key_prefix: string
            | null;
            cached_input_tokens: number;
            input_tokens: number;
            model: string | null;
            output_tokens: number;
            request_count: number;
            uncached_input_tokens: number;
            user_id: string | null;
        };
        ModelArchiveSource: {
            deployment: components["schemas"]["DeploymentArchivePayload"];
            disable_archive_download?: boolean;
            kind: "model_archive";
            name: string;
            s3_key?: string
            | null;
        };
        ModelConfig: {
            rate_limits?: components["schemas"]["RateLimit"][];
            slug: string;
            usage_limits?: components["schemas"]["UsageLimit"][];
        };
        ModelMetricDescriptor: {
            kind: components["schemas"]["ModelMetricKind"];
            label_sets: { [key: string]: string }[];
            name: string;
            unit_hint: components["schemas"]["ModelMetricUnitHint"];
        };
        ModelMetricKind: "GAUGE"
        | "COUNTER"
        | "HISTOGRAM";
        ModelMetricMode: "CURRENT" | "SUMMARY" | "SERIES";
        ModelMetricUnitHint:
            | "PER_SECOND"
            | "SECONDS"
            | "BYTES"
            | "MEBIBYTES"
            | "COUNT"
            | "RATIO";
        ModelMetricValueSet: {
            start_epoch_millis: number;
            values: (number | null)[][];
        };
        Models: { models: components["schemas"]["Model"][] };
        ModelTombstone: { deleted: boolean; id: string };
        Name:
            | "CREATED"
            | "DEPLOYING"
            | "RUNNING"
            | "SCALED_TO_ZERO"
            | "FAILED"
            | "STOPPED"
            | "PREEMPTED";
        OneTimeAutoscalingSchedule: {
            autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"];
            cadence: "ONE_TIME";
            enabled: boolean;
            end_at: string;
            id: string;
            name: string;
            start_at: string;
        };
        OneTimeAutoscalingScheduleUpsert: {
            autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"];
            cadence: "ONE_TIME";
            enabled: boolean;
            end_at: string;
            id?: string
            | null;
            name: string;
            start_at: string;
        };
        OrderBy: { field: string; order: string };
        OrganizationInfo: {
            aws_assume_role: components["schemas"]["AwsAssumeRole"] | null;
            created_at: string;
            name: string | null;
            org_id: string;
        };
        PaginationResponse: { cursor: string
        | null; has_more: boolean };
        PatchInteractiveSessionRequest: {
            timeout_minutes?: number | null;
            trigger?: components["schemas"]["V1InteractiveSessionTrigger"] | null;
        };
        PatchInteractiveSessionResponse: {
            interactive_session: components["schemas"]["InteractiveSession"];
            message: string;
        };
        PatchLoopsUserConfigRequest: {
            sampler_accelerator_priority?: string[]
            | null;
            trainer_accelerator_priority?: string[] | null;
        };
        PatchLoopsUserConfigResponse: {
            user_config: components["schemas"]["LoopsUserConfig"];
        };
        PatchTeamTrainingGpuCapacityRequest: {
            gpu_type: string;
            max_gpus: number;
            team_id: string;
        };
        PatchTeamTrainingGpuCapacityResponse: {
            team_gpu_capacity: components["schemas"]["TeamTrainingGpuCapacityItem"];
        };
        PendingJobAheadAtSubmit: {
            instance_type_name: string;
            priority: number;
            requested_gpus: number;
            submitted_at: string;
            training_job_id: string;
            training_job_name: string
            | null;
        };
        PrepareModelUploadRequest: {
            deployment: components["schemas"]["DeploymentArchivePayload"];
            dry_run?: boolean;
            model_id?: string
            | null;
            name?: string | null;
            team_id?: string | null;
        };
        PrepareModelUploadResponse: {
            creds: components["schemas"]["AWSCredentials"]
            | null;
            s3_bucket: string | null;
            s3_key: string | null;
            s3_region: string | null;
        };
        PromoteRequest: {
            preserve_env_instance_type?: boolean;
            scale_down_previous_production?: boolean;
        };
        PromoteToChainEnvironmentRequest: {
            deployment_id: string;
            scale_down_previous_deployment?: boolean;
        };
        PromoteToEnvironmentRequest: {
            deployment_id: string;
            preserve_env_instance_type?: boolean;
            scale_down_previous_deployment?: boolean;
        };
        PromotionCleanupStrategy: "KEEP"
        | "SCALE_TO_ZERO"
        | "DEACTIVATE";
        PromotionSettings: {
            promotion_cleanup_strategy:
                | components["schemas"]["PromotionCleanupStrategy"]
                | null;
            ramp_up_duration_seconds: number
            | null;
            ramp_up_while_promoting: boolean | null;
            redeploy_on_promotion: boolean | null;
            rolling_deploy: boolean | null;
            rolling_deploy_config: components["schemas"]["RollingDeployConfig"] | null;
        };
        QueueEvent: {
            created: string;
            event_message: string
            | null;
            exit_code: number | null;
            status: string;
            training_job_id: string;
            training_job_name: string | null;
        };
        RateLimit: {
            threshold: number;
            type: components["schemas"]["LimitType"];
            unit: components["schemas"]["RateLimitUnit"];
        };
        RateLimitUnit: "SECOND"
        | "MINUTE";
        RecreateTrainingJobResponse: {
            training_job: components["schemas"]["TrainingJob"];
        };
        Region: { display_name: string; slug: string };
        Regions: { regions: components["schemas"]["Region"][] };
        RegisterAPIKeyRequest: { key: string; name?: string | null };
        RegisterAPIKeyResponse: { ok: boolean };
        RegistrySecretDockerAuth: {
            secret_ref: components["schemas"]["SecretReference"];
        };
        RequestBackpressurePolicy: "QUEUE_ON_FULL"
        | "REJECT_ON_FULL";
        RequestBackpressureSettings: {
            policy: components["schemas"]["RequestBackpressurePolicy"] | null;
        };
        ResourceKind: | "LOOPS_SAMPLER"
        | "LOOPS_TRAINER"
        | "MODEL_DEPLOYMENT"
        | "TRAINING_JOB"
        | "CHAINLET";
        ResponseTimeDatapoint: {
            p50: number
            | null;
            p95: number | null;
            p99: number | null;
            timestamp: string;
        };
        RestoreVolumeVersionRequest: { expected_sequence?: number
        | null };
        RestoreVolumeVersionResponse: {
            digest: string;
            lifecycle: string;
            namespace: string;
            version_ref: string;
            volume: string;
            volume_sequence: number;
        };
        RetryDeploymentResponse: {
            deployment: components["schemas"]["Deployment"];
            reason: string
            | null;
            retried: boolean;
        };
        RollingDeployConfig: {
            max_surge_percent: number;
            max_unavailable_percent: number;
            replica_overhead_percent: number;
            rolling_deploy_strategy: components["schemas"]["RollingDeployStrategy"];
            stabilization_time_seconds: number;
        };
        RollingDeployStrategy: "REPLICA";
        SearchTrainingJobsRequest: {
            job_id?: string
            | null;
            order_by?: components["schemas"]["OrderBy"][];
            project_id?: string | null;
            statuses?: string[] | null;
        };
        SearchTrainingJobsResponse: {
            training_jobs: components["schemas"]["TrainingJob"][];
        };
        Secret: { created_at: string; id: string; name: string; team_name: string };
        SecretReference: { name: string };
        Secrets: { secrets: components["schemas"]["Secret"][] };
        SecretTombstone: { name: string };
        SharedEndpointRegion: "UNRESTRICTED" | "EU";
        SignalPromotionResponse: { success: boolean };
        SignSSHCertificateRequest: {
            public_key: string;
            replica_id?: string | null;
        };
        SignSSHCertificateResponse: {
            jwt: string;
            proxy_address: string;
            ssh_cert_expires_at: string;
            ssh_certificate: string;
        };
        SortOrder: "asc"
        | "desc";
        StopTrainingJobRequest: Record<string, unknown>;
        StopTrainingJobResponse: {
            training_job: components["schemas"]["TrainingJob"];
        };
        StorageMetrics: {
            usage_bytes: components["schemas"]["TrainingJobMetric"][];
            utilization: components["schemas"]["TrainingJobMetric"][];
        };
        SupportedModel: {
            max_context_length: number;
            model_name: string;
            supports_vision_language: boolean;
        };
        SyncDeploymentPatchesRequest: Record<string, unknown>;
        SyncDeploymentPatchesResponse: { needs_full_deploy_reason: string | null };
        Team: { created_at: string; default: boolean; id: string; name: string };
        Teams: { teams: components["schemas"]["Team"][] };
        TeamTrainingGpuCapacityItem: {
            baseline: number;
            dedicated_usage_count: number;
            gpu_type: string;
            limit: number;
            spot_usage_count: number;
            team_id: string;
            team_name: string;
            usage_count: number;
        };
        TerminateReplicaResponse: { success: boolean };
        TrainerCheckpointTarget: "sampler" | "trainer";
        TrainingGpuCapacityItem: {
            baseline: number;
            dedicated_usage_count: number;
            gpu_type: string;
            limit: number;
            spot_usage_count: number;
            usage_count: number;
        };
        TrainingItem: {
            billable_resource: components["schemas"]["BillableResource"];
            daily?: components["schemas"]["DailyTrainingUsage"][];
            minutes: number;
            subtotal: number
            | string;
        };
        TrainingJob: {
            availability_model: components["schemas"]["V1AvailabilityModel"];
            checkpoint_sync_status: | components["schemas"]["CheckpointSyncStatus"]
            | null;
            created_at: string;
            current_status: string;
            error_message: string
            | null;
            id: string;
            instance_type: components["schemas"]["InstanceType"];
            name: string | null;
            node_count: number;
            priority: number;
            training_project: components["schemas"]["TrainingProjectSummary"];
            training_project_id: string;
            updated_at: string;
            user: components["schemas"]["User"] | null;
        };
        TrainingJobCheckpoint: {
            base_model: string
            | null;
            checkpoint_id: string;
            checkpoint_type: string;
            created_at: string;
            lora_adapter_config: { [key: string]: unknown } | null;
            size_bytes: number;
            sync_status: string | null;
            training_job_id: string;
        };
        TrainingJobMetric: { timestamp: string; value: number };
        TrainingJobMetrics: {
            cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
            cpu_usage: components["schemas"]["TrainingJobMetric"][];
            ephemeral_storage: components["schemas"]["StorageMetrics"];
            gpu_memory_usage_bytes: {
                [key: string]: { timestamp: string; value: number }[];
            };
            gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
        };
        TrainingJobNodeMetrics: {
            metrics: components["schemas"]["TrainingJobMetrics"];
            node_id: string;
        };
        TrainingJobTombstone: {
            deleted: boolean;
            id: string;
            training_project_id: string;
        };
        TrainingProject: {
            created_at: string;
            id: string;
            latest_job: components["schemas"]["TrainingJob"]
            | null;
            name: string;
            team_name: string | null;
            updated_at: string;
        };
        TrainingProjectSummary: { id: string; name: string };
        TrainingProjectTombstone: { deleted: boolean; id: string };
        TrainingUsage: {
            breakdown?: components["schemas"]["TrainingItem"][];
            credits_used: number | string;
            minutes: number;
            subtotal: number | string;
            total: number | string;
        };
        TrainingWeightAuth: {
            auth_method: components["schemas"]["AuthMethod"];
            auth_secret_name?: string
            | null;
            aws_assume_role_arn?: string | null;
            aws_assume_role_region?: string | null;
            aws_oidc_region?: string | null;
            aws_oidc_role_arn?: string | null;
            gcp_oidc_service_account?: string | null;
            gcp_oidc_workload_id_provider?: string | null;
        };
        TrussUserEnv: {
            git_info?: components["schemas"]["GitInfo"]
            | null;
            is_frontend_deployment?: boolean;
            is_library_deployment?: boolean;
            mypy_version?: string | null;
            pydantic_version?: string | null;
            python_version?: string | null;
            truss_client_version?: string | null;
        };
        TTSBenchmarkMetrics: {
            cost_per_audio_minute_usd?: number
            | null;
            max_concurrent_streams_at_rtf1?: number | null;
            ttft_ms_p50?: number | null;
            ttft_ms_p50_at_max_concurrency?: number | null;
        };
        UpdateAutoscalingScheduleSettings: {
            delete_schedules?: string[];
            schedules?: (
                | components["schemas"]["AutoscalingScheduleUpsert"]
                | components["schemas"]["OneTimeAutoscalingScheduleUpsert"]
            )[];
            timezone?: string
            | null;
        };
        UpdateAutoscalingSettings: {
            autoscaling_window?: number
            | null;
            concurrency_target?: number | null;
            max_replica?: number | null;
            max_scale_down_rate?: number | null;
            min_replica?: number | null;
            scale_down_delay?: number | null;
            target_in_flight_tokens?: number | null;
            target_utilization_percentage?: number | null;
        };
        UpdateAutoscalingSettingsResponse: {
            message: string;
            status: components["schemas"]["UpdateAutoscalingSettingsStatus"];
        };
        UpdateAutoscalingSettingsStatus: "ACCEPTED"
        | "QUEUED"
        | "UNCHANGED";
        UpdateChainEnvironmentRequest: {
            promotion_settings?:
                | components["schemas"]["UpdatePromotionSettings"]
                | null;
        };
        UpdateChainEnvironmentResponse: { ok: boolean };
        UpdateChainletEnvironmentAutoscalingSettingsRequest: {
            updates: components["schemas"]["ChainletEnvironmentAutoscalingSettingsUpdate"][];
        };
        UpdateChainletEnvironmentInstanceTypeRequest: {
            updates: components["schemas"]["ChainletEnvironmentInstanceTypeUpdate"][];
        };
        UpdateChainletEnvironmentInstanceTypeResponse: {
            chain_deployment: components["schemas"]["ChainDeployment"]
            | null;
            chainlet_environment_settings: components["schemas"]["ChainletEnvironmentSettings"][];
            requires_redeployment: boolean;
        };
        UpdateDeploymentRequest: { name?: string
        | null };
        UpdateEndpointRequest: {
            targets?: components["schemas"]["EndpointTargetRequest"][] | null;
        };
        UpdateEnvironmentGroupManageAccess: {
            is_restricted: boolean;
            user_ids?: string[];
        };
        UpdateEnvironmentGroupRequest: {
            manage_access?: | components["schemas"]["UpdateEnvironmentGroupManageAccess"]
            | null;
        };
        UpdateEnvironmentRequest: {
            autoscaling_schedule_settings?: | components["schemas"]["UpdateAutoscalingScheduleSettings"]
            | null;
            autoscaling_settings?: | components["schemas"]["UpdateAutoscalingSettings"]
            | null;
            promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
            | null;
            request_backpressure_settings?: | components["schemas"]["UpdateRequestBackpressureSettings"]
            | null;
        };
        UpdateEnvironmentResponse: {
            environment: components["schemas"]["Environment"];
            message: string;
            status: components["schemas"]["UpdateAutoscalingSettingsStatus"];
        };
        UpdateGroupMetadata: { name?: string
        | null };
        UpdateGroupRequest: {
            metadata?: components["schemas"]["UpdateGroupMetadata"] | null;
            models?: components["schemas"]["ModelConfig"][] | null;
        };
        UpdateLibraryListingRequest: {
            display_name?: string
            | null;
            is_public?: boolean | null;
            metadata?: components["schemas"]["LibraryListingMetadata"] | null;
            trending?: boolean | null;
        };
        UpdateLibraryListingVersionRequest: {
            allow_truss_download?: boolean
            | null;
            benchmark?: components["schemas"]["BenchmarkSnapshot"] | null;
            is_live?: boolean | null;
        };
        UpdatePromotionSettings: {
            promotion_cleanup_strategy?: | components["schemas"]["PromotionCleanupStrategy"]
            | null;
            ramp_up_duration_seconds?: number
            | null;
            ramp_up_while_promoting?: boolean | null;
            redeploy_on_promotion?: boolean | null;
            rolling_deploy?: boolean | null;
            rolling_deploy_config?:
                | components["schemas"]["UpdateRollingDeployConfig"]
                | null;
        };
        UpdateRequestBackpressureSettings: {
            policy?: components["schemas"]["RequestBackpressurePolicy"]
            | null;
        };
        UpdateRollingDeployConfig: {
            max_surge_percent?: number
            | null;
            max_unavailable_percent?: number | null;
            replica_overhead_percent?: number | null;
            rolling_deploy_strategy?:
                | components["schemas"]["RollingDeployStrategy"]
                | null;
            stabilization_time_seconds?: number
            | null;
        };
        UpdateTrainingJobRequest: {
            availability_model?: | components["schemas"]["V1AvailabilityModel"]
            | null;
            priority?: number
            | null;
        };
        UpdateTrainingJobResponse: {
            training_job: components["schemas"]["TrainingJob"];
        };
        UpsertSecretRequest: { name: string; value: string };
        UpsertTrainingProject: { name: string };
        UpsertTrainingProjectRequest: {
            training_project: components["schemas"]["UpsertTrainingProject"];
        };
        UpsertTrainingProjectResponse: {
            training_project: components["schemas"]["TrainingProject"];
        };
        UsageDimension: "api_key"
        | "user"
        | "model";
        UsageLimit: {
            threshold: number;
            type: components["schemas"]["LimitType"];
            unit: components["schemas"]["UsageLimitUnit"];
        };
        UsageLimitUnit: "DAY";
        UsageSummary: {
            dedicated_usage: components["schemas"]["DedicatedUsage"]
            | null;
            model_apis_usage: components["schemas"]["ModelApisUsage"] | null;
            training_usage: components["schemas"]["TrainingUsage"] | null;
        };
        User: { email: string
        | null };
        UserInfo: {
            email: string | null;
            name: string | null;
            user_id: string;
            workspace_name: string | null;
        };
        UsersResponse: {
            items: components["schemas"]["UserInfo"][];
            pagination: components["schemas"]["PaginationResponse"];
        };
        V1AvailabilityModel: "dedicated"
        | "spot";
        V1InteractiveSessionAuthProvider: "github" | "microsoft";
        V1InteractiveSessionProvider: "vs_code" | "cursor" | "ssh";
        V1InteractiveSessionTrigger: "on_startup" | "on_failure" | "on_demand";
        ValidateLoopsCheckpointRequest: { checkpoint_path: string };
        ValidateLoopsCheckpointResponse: Record<string, unknown>;
        VertexTargetConfig: { location: string; project_id: string };
        Volume: {
            head: components["schemas"]["VolumeVersionSummary"] | null;
            name: string;
            namespace: string;
            sequence: number;
            tag_count: number;
            tags: components["schemas"]["VolumeTag"][];
            updated_at: string;
            version_ref: string;
            versions_alive: number;
            versions_tombstoned: number;
            versions_untagged: number;
        };
        VolumeTag: { digest: string; name: string };
        VolumeTokenScope: "PULL" | "INSPECT" | "PUSH" | "TAG";
        VolumeVersion: {
            created_at: string;
            delete_after: string | null;
            digest: string;
            is_head: boolean;
            lifecycle: string;
            namespace: string;
            sequence: number | null;
            tags: string[];
            tombstoned_at: string | null;
            total_size_bytes: number | null;
            version_ref: string;
            volume: string;
        };
        VolumeVersionDetail: {
            created_at: string;
            delete_after: string
            | null;
            digest: string;
            entry_count: number | null;
            is_head: boolean;
            lifecycle: string;
            namespace: string;
            sequence: number | null;
            tags: string[];
            tombstoned_at: string | null;
            total_size_bytes: number | null;
            version_ref: string;
            volume: string;
            volume_sequence: number;
        };
        VolumeVersionSummary: {
            created_at: string;
            digest: string;
            total_size_bytes: number;
        };
    }

    Type Declaration

    • ActivateResponse: { no_op: boolean; success: boolean }

      ActivateResponseV1

      The response to a request to activate a deployment.

      • no_op: boolean

        No Op

        Whether the request did nothing because the deployment was already active or on its way to becoming active

        false
        
      • success: boolean

        Success

        Whether the deployment was successfully activated

        true
        
    • ActiveJobAtSubmit: {
          instance_type_name: string;
          status_at_submit: string;
          status_set_at: string;
          total_gpus: number;
          training_job_id: string;
          training_job_name: string | null;
          workload_plane_name: string;
      }

      ActiveJobAtSubmitV1

      One other job in the same (org, gpu_type) pool that was holding GPU capacity at the moment the target was submitted.

      • instance_type_name: string

        Instance Type Name

        Instance type of the other job

      • status_at_submit: string

        Status At Submit

        Other job's status as of submitted_at (one of ACTIVE_STATES)

      • status_set_at: string

        Status Set At Format: date-time

        When that status was set

      • total_gpus: number

        Total Gpus

        gpu_count * effective_node_count

      • training_job_id: string

        Training Job Id

        Hashid of the other training job

      • training_job_name: string | null

        Training Job Name

        Other job's name

        null
        
      • workload_plane_name: string

        Workload Plane Name

        Workload plane the other job was on

    • APIKey: { api_key: string }

      APIKeyV1

      Represents an API key.

      • api_key: string

        Api Key

        The API key string

    • APIKeyCategory:
          | "PERSONAL"
          | "ROUTES"
          | "WORKSPACE_MANAGE_ALL"
          | "WORKSPACE_EXPORT_METRICS"
          | "WORKSPACE_INVOKE"
          | "WORKSPACE_MANAGE_API_KEYS"

      APIKeyCategory

      Enum representing the category of an API key.

    • APIKeyInfo: {
          model_ids: string[] | null;
          name: string | null;
          owner: components["schemas"]["APIKeyOwner"] | null;
          prefix: string;
          team_name: string | null;
          type: components["schemas"]["APIKeyCategory"];
      }

      APIKeyInfoV1

      Represents the metadata of an API key.

      • model_ids: string[] | null

        Model Ids

        List of model IDs to scope the API key to, only present if type is 'WORKSPACE_EXPORT_METRICS' or 'WORKSPACE_INVOKE'

        null
        
        [
        "aaaaaaaa"
        ]
      • name: string | null

        Name

        Optional name for the API key

        null
        
        my-api-key
        
      • owner: components["schemas"]["APIKeyOwner"] | null

        The user who owns the API key. Only present for personal API keys.

        null
        
      • prefix: string

        Prefix

        The prefix of the API key

      • team_name: string | null

        Team Name

        The name of the team associated with the API key

        null
        
      • type: components["schemas"]["APIKeyCategory"]

        Type of the API key.

        PERSONAL
        
        WORKSPACE_MANAGE_API_KEYS
        
        WORKSPACE_EXPORT_METRICS
        
        WORKSPACE_INVOKE
        
        WORKSPACE_MANAGE_ALL
        
    • APIKeyOwner: { email: string | null; name: string | null; user_id: string }

      APIKeyOwnerV1

      The user who owns a personal API key.

      • email: string | null

        Email

        Email address of the user

        null
        
      • name: string | null

        Name

        Display name of the user

        null
        
      • user_id: string

        User Id

        Unique identifier for the user

    • APIKeys: { keys: components["schemas"]["APIKeyInfo"][] }

      APIKeysV1

      A list of API keys.

    • APIKeyTombstone: { prefix: string }

      APIKeyTombstoneV1

      An API key tombstone.

      • prefix: string

        Prefix

        Unique prefix of the API key

    • AuditLogActor: {
          api_key_name: string | null;
          api_key_prefix: string | null;
          email: string | null;
          type: components["schemas"]["AuditLogActorType"];
      }

      AuditLogActorV1

      The actor that performed an audited action.

      • api_key_name: string | null

        Api Key Name

        Display name of the acting API key, when the actor is an API key.

        null
        
      • api_key_prefix: string | null

        Api Key Prefix

        Prefix of the acting API key, when the actor is an API key.

        null
        
      • email: string | null

        Email

        Email of the acting user, when the actor is a user.

        null
        
      • type: components["schemas"]["AuditLogActorType"]

        Kind of actor that performed the action.

    • AuditLogActorType: "USER" | "API_KEY" | "BASETEN_USER" | "BASETEN_SYSTEM" | "TOMBSTONE_USER"

      AuditLogActorTypeV1

      Kind of actor that performed an audited action.

    • AuditLogApiKeyType:
          | "PERSONAL"
          | "CREATOR_SERVICE_ACCOUNT"
          | "MANAGE_API_KEYS_SERVICE_ACCOUNT"
          | "INVOKE_ALL_MODELS_SERVICE_ACCOUNT"
          | "INVOKE_ALLOWED_MODELS_SERVICE_ACCOUNT"
          | "INVOKE_SCOPED_ENVS_AND_MODELS_SERVICE_ACCOUNT"
          | "EXPORT_METRICS_ALL_MODELS_SERVICE_ACCOUNT"
          | "EXPORT_METRICS_ALLOWED_MODELS_SERVICE_ACCOUNT"
          | "INVOKE_ALL_SHARED_ENDPOINTS_SERVICE_ACCOUNT"
          | "INVOKE_ALLOWED_SHARED_ENDPOINTS_SERVICE_ACCOUNT"
          | "INVOKE_ALL_ROUTES"

      AuditLogApiKeyTypeV1

      Type of API key recorded on an API-key event.

    • AuditLogEntry: {
          actor: components["schemas"]["AuditLogActor"];
          client_name: string | null;
          client_session_id: string | null;
          client_version: string | null;
          created: string;
          event_data:
              | components["schemas"]["AuditLogEventModelDeployed"]
              | components["schemas"]["AuditLogEventModelDeploymentActivated"]
              | components["schemas"]["AuditLogEventModelDeploymentDeactivated"]
              | components["schemas"]["AuditLogEventModelDeploymentRetried"]
              | components["schemas"]["AuditLogEventModelDeploymentPromoted"]
              | components["schemas"]["AuditLogEventModelDeploymentAutoscalingSettingsChanged"]
              | components["schemas"]["AuditLogEventModelDeploymentRequestBackpressureSettingsChanged"]
              | components["schemas"]["AuditLogEventModelDeploymentInstanceTypeChanged"]
              | components["schemas"]["AuditLogEventModelDeploymentDeleted"]
              | components["schemas"]["AuditLogEventModelDeleted"]
              | components["schemas"]["AuditLogEventChainDeployed"]
              | components["schemas"]["AuditLogEventChainDeploymentActivated"]
              | components["schemas"]["AuditLogEventChainDeploymentDeactivated"]
              | components["schemas"]["AuditLogEventChainDeploymentPromoted"]
              | components["schemas"]["AuditLogEventChainletAutoscalingSettingsChanged"]
              | components["schemas"]["AuditLogEventChainletInstanceTypeChanged"]
              | components["schemas"]["AuditLogEventChainDeploymentDeleted"]
              | components["schemas"]["AuditLogEventChainDeleted"]
              | components["schemas"]["AuditLogEventChainEnvironmentCreated"]
              | components["schemas"]["AuditLogEventChainEnvironmentUpdated"]
              | components["schemas"]["AuditLogEventSecretUpdated"]
              | components["schemas"]["AuditLogEventSecretDeleted"]
              | components["schemas"]["AuditLogEventApiKeyCreated"]
              | components["schemas"]["AuditLogEventApiKeyDeleted"]
              | components["schemas"]["AuditLogEventGatewayEndpointCreated"]
              | components["schemas"]["AuditLogEventGatewayEndpointUpdated"]
              | components["schemas"]["AuditLogEventGatewayEndpointDeleted"]
              | components["schemas"]["AuditLogEventUserInvited"]
              | components["schemas"]["AuditLogEventUserJoinedOrganization"]
              | components["schemas"]["AuditLogEventWebhookSigningSecretCreated"]
              | components["schemas"]["AuditLogEventWebhookSigningSecretRotated"]
              | components["schemas"]["AuditLogEventWebhookSigningSecretDeleted"]
              | components["schemas"]["AuditLogEventUserRoleUpdated"]
              | components["schemas"]["AuditLogEventUserTeamRoleUpdated"]
              | components["schemas"]["AuditLogEventUserRemoved"]
              | components["schemas"]["AuditLogEventDirectoryGroupRoleUpdated"]
              | components["schemas"]["AuditLogEventRequireGroupBasedAdminsEnabled"]
              | components["schemas"]["AuditLogEventEnvironmentCreated"]
              | components["schemas"]["AuditLogEventEnvironmentUpdated"]
              | components["schemas"]["AuditLogEventEnvironmentDeleted"]
              | components["schemas"]["AuditLogEventReplicaTerminated"]
              | components["schemas"]["AuditLogEventModelPromotionControlAction"]
              | components["schemas"]["AuditLogEventSshCertificateSigned"]
              | components["schemas"]["AuditLogEventVolumeDeleted"]
              | components["schemas"]["AuditLogEventVolumeVersionDeleted"]
              | components["schemas"]["AuditLogEventVolumeVersionRestored"];
          event_type: components["schemas"]["AuditLogEventType"];
          id: string;
          source: components["schemas"]["AuditLogSource"]
          | null;
      }

      AuditLogEntryV1

      A single audit-log entry.

    • AuditLogEventApiKeyCreated: {
          api_key_id: string;
          api_key_type: components["schemas"]["AuditLogApiKeyType"];
          event_type: "API_KEY_CREATED";
          prefix: string;
      }

      AuditLogEventApiKeyCreatedV1

      An API key was created.

      • api_key_id: string

        Api Key Id

      • api_key_type: components["schemas"]["AuditLogApiKeyType"]
      • event_type: "API_KEY_CREATED"

        discriminator enum property added by openapi-typescript

      • prefix: string

        Prefix

    • AuditLogEventApiKeyDeleted: {
          api_key_id: string;
          api_key_type: components["schemas"]["AuditLogApiKeyType"];
          event_type: "API_KEY_DELETED";
          prefix: string;
      }

      AuditLogEventApiKeyDeletedV1

      An API key was revoked.

      • api_key_id: string

        Api Key Id

      • api_key_type: components["schemas"]["AuditLogApiKeyType"]
      • event_type: "API_KEY_DELETED"

        discriminator enum property added by openapi-typescript

      • prefix: string

        Prefix

    • AuditLogEventAutoscalingScheduleAction: "CREATED" | "UPDATED" | "DELETED" | "UNCHANGED"

      AuditLogEventAutoscalingScheduleActionV1

      What an autoscaling change did to one schedule.

    • AuditLogEventAutoscalingScheduleChange: {
          action: components["schemas"]["AuditLogEventAutoscalingScheduleAction"];
          current:
              | components["schemas"]["AuditLogEventAutoscalingScheduleSettings"]
              | null;
          previous: | components["schemas"]["AuditLogEventAutoscalingScheduleSettings"]
          | null;
          schedule_id: string;
      }

      AuditLogEventAutoscalingScheduleChangeV1

      What an autoscaling change did to one schedule, and the schedule on either side of it. previous is null on a create, current on a delete, and an unchanged schedule carries only current. Not itself a payload in the discriminated union.

    • AuditLogEventAutoscalingScheduleSettings: {
          autoscaling_window: number | null;
          cadence: string;
          concurrency_target: number | null;
          enabled: boolean;
          end_at: string | null;
          end_hour: number | null;
          end_minute: number | null;
          max_replica: number;
          max_scale_down_rate: number | null;
          min_replica: number;
          scale_down_delay: number | null;
          schedule_name: string;
          start_at: string | null;
          start_hour: number | null;
          start_minute: number | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
          timezone: string;
          weekdays: string[] | null;
      }

      AuditLogEventAutoscalingScheduleSettingsV1

      One autoscaling schedule's timing and autoscaling settings. Not itself a union payload.

      • autoscaling_window: number | null

        Autoscaling Window

      • cadence: string

        Cadence

      • concurrency_target: number | null

        Concurrency Target

      • enabled: boolean

        Enabled

      • end_at: string | null

        End At

        null
        
      • end_hour: number | null

        End Hour

      • end_minute: number | null

        End Minute

      • max_replica: number

        Max Replica

      • max_scale_down_rate: number | null

        Max Scale Down Rate

      • min_replica: number

        Min Replica

      • scale_down_delay: number | null

        Scale Down Delay

      • schedule_name: string

        Schedule Name

      • start_at: string | null

        Start At

        null
        
      • start_hour: number | null

        Start Hour

      • start_minute: number | null

        Start Minute

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

      • target_utilization_percentage: number | null

        Target Utilization Percentage

      • timezone: string

        Timezone

      • weekdays: string[] | null

        Weekdays

    • AuditLogEventAutoscalingSettings: {
          autoscaling_window: number | null;
          concurrency_target: number;
          max_replica: number;
          max_scale_down_rate: number | null;
          min_replica: number;
          scale_down_delay: number | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AuditLogEventAutoscalingSettingsV1

      Autoscaling settings for a deployment or environment.

      • autoscaling_window: number | null

        Autoscaling Window

      • concurrency_target: number

        Concurrency Target

      • max_replica: number

        Max Replica

      • max_scale_down_rate: number | null

        Max Scale Down Rate

      • min_replica: number

        Min Replica

      • scale_down_delay: number | null

        Scale Down Delay

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

      • target_utilization_percentage: number | null

        Target Utilization Percentage

    • AuditLogEventChainDeleted: {
          chain_deployment_name: string | null;
          chain_id: string;
          chain_name: string;
          event_type: "CHAIN_DELETED";
      }

      AuditLogEventChainDeletedV1

      A chain was deleted.

      • chain_deployment_name: string | null

        Chain Deployment Name

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • event_type: "CHAIN_DELETED"

        discriminator enum property added by openapi-typescript

    • AuditLogEventChainDeployed: {
          chain_deployment_id: string;
          chain_deployment_name: string | null;
          chain_id: string;
          chain_name: string;
          event_type: "CHAIN_DEPLOYED";
          is_primary: boolean;
          publish: boolean;
      }

      AuditLogEventChainDeployedV1

      A chain deployment was created.

      • chain_deployment_id: string

        Chain Deployment Id

      • chain_deployment_name: string | null

        Chain Deployment Name

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • event_type: "CHAIN_DEPLOYED"

        discriminator enum property added by openapi-typescript

      • is_primary: boolean

        Is Primary

      • publish: boolean

        Publish

    • AuditLogEventChainDeploymentActivated: {
          chain_deployment_id: string;
          chain_deployment_name: string | null;
          chain_id: string;
          chain_name: string;
          event_type: "CHAIN_DEPLOYMENT_ACTIVATED";
      }

      AuditLogEventChainDeploymentActivatedV1

      A chain deployment was activated.

      • chain_deployment_id: string

        Chain Deployment Id

      • chain_deployment_name: string | null

        Chain Deployment Name

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • event_type: "CHAIN_DEPLOYMENT_ACTIVATED"

        discriminator enum property added by openapi-typescript

    • AuditLogEventChainDeploymentDeactivated: {
          chain_deployment_id: string;
          chain_deployment_name: string | null;
          chain_id: string;
          chain_name: string;
          event_type: "CHAIN_DEPLOYMENT_DEACTIVATED";
      }

      AuditLogEventChainDeploymentDeactivatedV1

      A chain deployment was deactivated.

      • chain_deployment_id: string

        Chain Deployment Id

      • chain_deployment_name: string | null

        Chain Deployment Name

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • event_type: "CHAIN_DEPLOYMENT_DEACTIVATED"

        discriminator enum property added by openapi-typescript

    • AuditLogEventChainDeploymentDeleted: {
          chain_deployment_id: string;
          chain_id: string;
          chain_name: string;
          deployment_name: string | null;
          event_type: "CHAIN_DEPLOYMENT_DELETED";
      }

      AuditLogEventChainDeploymentDeletedV1

      A chain deployment was deleted.

      • chain_deployment_id: string

        Chain Deployment Id

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • deployment_name: string | null

        Deployment Name

      • event_type: "CHAIN_DEPLOYMENT_DELETED"

        discriminator enum property added by openapi-typescript

    • AuditLogEventChainDeploymentPromoted: {
          chain_deployment_id: string;
          chain_deployment_name: string | null;
          chain_id: string;
          chain_name: string;
          environment_id: string | null;
          environment_name: string | null;
          event_type: "CHAIN_DEPLOYMENT_PROMOTED";
      }

      AuditLogEventChainDeploymentPromotedV1

      A chain deployment was promoted to an environment.

      • chain_deployment_id: string

        Chain Deployment Id

      • chain_deployment_name: string | null

        Chain Deployment Name

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • environment_id: string | null

        Environment Id

      • environment_name: string | null

        Environment Name

      • event_type: "CHAIN_DEPLOYMENT_PROMOTED"

        discriminator enum property added by openapi-typescript

    • AuditLogEventChainEnvironmentCreated: {
          chain_id: string;
          chain_name: string;
          environment_name: string;
          event_type: "CHAIN_ENVIRONMENT_CREATED";
          ramp_up_duration_seconds: number | null;
          ramp_up_while_promoting: boolean | null;
          redeploy_on_promotion: boolean | null;
      }

      AuditLogEventChainEnvironmentCreatedV1

      A chain environment was created.

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • environment_name: string

        Environment Name

      • event_type: "CHAIN_ENVIRONMENT_CREATED"

        discriminator enum property added by openapi-typescript

      • ramp_up_duration_seconds: number | null

        Ramp Up Duration Seconds

      • ramp_up_while_promoting: boolean | null

        Ramp Up While Promoting

      • redeploy_on_promotion: boolean | null

        Redeploy On Promotion

    • AuditLogEventChainEnvironmentUpdated: {
          chain_id: string;
          chain_name: string;
          environment_name: string;
          event_type: "CHAIN_ENVIRONMENT_UPDATED";
          ramp_up_duration_seconds: number | null;
          ramp_up_while_promoting: boolean | null;
          redeploy_on_promotion: boolean | null;
      }

      AuditLogEventChainEnvironmentUpdatedV1

      A chain environment was updated.

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • environment_name: string

        Environment Name

      • event_type: "CHAIN_ENVIRONMENT_UPDATED"

        discriminator enum property added by openapi-typescript

      • ramp_up_duration_seconds: number | null

        Ramp Up Duration Seconds

      • ramp_up_while_promoting: boolean | null

        Ramp Up While Promoting

      • redeploy_on_promotion: boolean | null

        Redeploy On Promotion

    • AuditLogEventChainletAutoscalingSettingsChanged: {
          autoscaling_window: number | null;
          chain_deployment_id: string;
          chain_deployment_name: string | null;
          chain_id: string;
          chain_name: string;
          chainlet_id: string;
          chainlet_name: string;
          concurrency_target: number;
          event_type: "CHAINLET_AUTOSCALING_SETTINGS_CHANGED";
          max_replica: number;
          max_scale_down_rate: number | null;
          min_replica: number;
          previous_settings:
              | components["schemas"]["AuditLogEventAutoscalingSettings"]
              | null;
          scale_down_delay: number
          | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AuditLogEventChainletAutoscalingSettingsChangedV1

      A chainlet's autoscaling settings were changed.

      • autoscaling_window: number | null

        Autoscaling Window

      • chain_deployment_id: string

        Chain Deployment Id

      • chain_deployment_name: string | null

        Chain Deployment Name

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • chainlet_id: string

        Chainlet Id

      • chainlet_name: string

        Chainlet Name

      • concurrency_target: number

        Concurrency Target

      • event_type: "CHAINLET_AUTOSCALING_SETTINGS_CHANGED"

        discriminator enum property added by openapi-typescript

      • max_replica: number

        Max Replica

      • max_scale_down_rate: number | null

        Max Scale Down Rate

      • min_replica: number

        Min Replica

      • previous_settings: components["schemas"]["AuditLogEventAutoscalingSettings"] | null
      • scale_down_delay: number | null

        Scale Down Delay

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

      • target_utilization_percentage: number | null

        Target Utilization Percentage

    • AuditLogEventChainletInstanceTypeChanged: {
          chain_deployment_id: string;
          chain_deployment_name: string | null;
          chain_id: string;
          chain_name: string;
          chainlet_id: string;
          chainlet_name: string;
          event_type: "CHAINLET_INSTANCE_TYPE_CHANGED";
          instance_type_name: string;
      }

      AuditLogEventChainletInstanceTypeChangedV1

      A chainlet's instance type was changed.

      • chain_deployment_id: string

        Chain Deployment Id

      • chain_deployment_name: string | null

        Chain Deployment Name

      • chain_id: string

        Chain Id

      • chain_name: string

        Chain Name

      • chainlet_id: string

        Chainlet Id

      • chainlet_name: string

        Chainlet Name

      • event_type: "CHAINLET_INSTANCE_TYPE_CHANGED"

        discriminator enum property added by openapi-typescript

      • instance_type_name: string

        Instance Type Name

    • AuditLogEventDirectoryGroupRoleUpdated: {
          directory_group_id: string;
          directory_group_name: string;
          event_type: "DIRECTORY_GROUP_ROLE_UPDATED";
          new_role_name: string;
          team_id: string | null;
          team_name: string | null;
      }

      AuditLogEventDirectoryGroupRoleUpdatedV1

      A directory group's role was updated.

      • directory_group_id: string

        Directory Group Id

      • directory_group_name: string

        Directory Group Name

      • event_type: "DIRECTORY_GROUP_ROLE_UPDATED"

        discriminator enum property added by openapi-typescript

      • new_role_name: string

        New Role Name

      • team_id: string | null

        Team Id

      • team_name: string | null

        Team Name

    • AuditLogEventEnvironmentCreated: {
          autoscaling_window: number | null;
          concurrency_target: number;
          deployment_type: string | null;
          environment_name: string;
          event_type: "ENVIRONMENT_CREATED";
          max_replica: number;
          max_scale_down_rate: number | null;
          max_surge_percent: number | null;
          max_unavailable_percent: number | null;
          min_replica: number;
          model_id: string;
          model_name: string;
          promotion_cleanup_strategy: string | null;
          ramp_up_duration_seconds: number | null;
          ramp_up_step_size: number | null;
          ramp_up_while_promoting: boolean | null;
          redeploy_on_promotion: boolean | null;
          replica_overhead_percent: number | null;
          request_backpressure_policy: string | null;
          rolling_deploy: boolean | null;
          rolling_deploy_strategy: string | null;
          scale_down_delay: number | null;
          stabilization_time_seconds: number | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AuditLogEventEnvironmentCreatedV1

      A model environment was created.

      • autoscaling_window: number | null

        Autoscaling Window

      • concurrency_target: number

        Concurrency Target

      • deployment_type: string | null

        Deployment Type

      • environment_name: string

        Environment Name

      • event_type: "ENVIRONMENT_CREATED"

        discriminator enum property added by openapi-typescript

      • max_replica: number

        Max Replica

      • max_scale_down_rate: number | null

        Max Scale Down Rate

      • max_surge_percent: number | null

        Max Surge Percent

      • max_unavailable_percent: number | null

        Max Unavailable Percent

      • min_replica: number

        Min Replica

      • model_id: string

        Model Id

      • model_name: string

        Model Name

      • promotion_cleanup_strategy: string | null

        Promotion Cleanup Strategy

      • ramp_up_duration_seconds: number | null

        Ramp Up Duration Seconds

      • ramp_up_step_size: number | null

        Ramp Up Step Size

      • ramp_up_while_promoting: boolean | null

        Ramp Up While Promoting

      • redeploy_on_promotion: boolean | null

        Redeploy On Promotion

      • replica_overhead_percent: number | null

        Replica Overhead Percent

      • request_backpressure_policy: string | null

        Request Backpressure Policy

        null
        
      • rolling_deploy: boolean | null

        Rolling Deploy

      • rolling_deploy_strategy: string | null

        Rolling Deploy Strategy

      • scale_down_delay: number | null

        Scale Down Delay

      • stabilization_time_seconds: number | null

        Stabilization Time Seconds

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

      • target_utilization_percentage: number | null

        Target Utilization Percentage

    • AuditLogEventEnvironmentDeleted: {
          environment_name: string;
          event_type: "ENVIRONMENT_DELETED";
          model_id: string;
          model_name: string;
      }

      AuditLogEventEnvironmentDeletedV1

      A model environment was deleted.

      • environment_name: string

        Environment Name

      • event_type: "ENVIRONMENT_DELETED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventEnvironmentSettings: {
          autoscaling_window: number | null;
          concurrency_target: number;
          max_replica: number;
          max_scale_down_rate: number | null;
          max_surge_percent: number | null;
          max_unavailable_percent: number | null;
          min_replica: number;
          promotion_cleanup_strategy: string | null;
          ramp_up_duration_seconds: number | null;
          ramp_up_step_size: number | null;
          ramp_up_while_promoting: boolean | null;
          redeploy_on_promotion: boolean | null;
          replica_overhead_percent: number | null;
          request_backpressure_policy: string | null;
          rolling_deploy: boolean | null;
          rolling_deploy_strategy: string | null;
          scale_down_delay: number | null;
          stabilization_time_seconds: number | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AuditLogEventEnvironmentSettingsV1

      Full environment settings (autoscaling + rolling promotion + deprecated canary); shared base for the environment events and the type of their previous_settings snapshots. Not itself a payload in the discriminated union.

      • autoscaling_window: number | null

        Autoscaling Window

      • concurrency_target: number

        Concurrency Target

      • max_replica: number

        Max Replica

      • max_scale_down_rate: number | null

        Max Scale Down Rate

      • max_surge_percent: number | null

        Max Surge Percent

      • max_unavailable_percent: number | null

        Max Unavailable Percent

      • min_replica: number

        Min Replica

      • promotion_cleanup_strategy: string | null

        Promotion Cleanup Strategy

      • ramp_up_duration_seconds: number | null

        Ramp Up Duration Seconds

      • ramp_up_step_size: number | null

        Ramp Up Step Size

      • ramp_up_while_promoting: boolean | null

        Ramp Up While Promoting

      • redeploy_on_promotion: boolean | null

        Redeploy On Promotion

      • replica_overhead_percent: number | null

        Replica Overhead Percent

      • request_backpressure_policy: string | null

        Request Backpressure Policy

        null
        
      • rolling_deploy: boolean | null

        Rolling Deploy

      • rolling_deploy_strategy: string | null

        Rolling Deploy Strategy

      • scale_down_delay: number | null

        Scale Down Delay

      • stabilization_time_seconds: number | null

        Stabilization Time Seconds

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

      • target_utilization_percentage: number | null

        Target Utilization Percentage

    • AuditLogEventEnvironmentUpdated: {
          autoscaling_window: number | null;
          concurrency_target: number;
          deployment_type: string | null;
          environment_name: string;
          event_type: "ENVIRONMENT_UPDATED";
          max_replica: number;
          max_scale_down_rate: number | null;
          max_surge_percent: number | null;
          max_unavailable_percent: number | null;
          min_replica: number;
          model_id: string;
          model_name: string;
          previous_settings:
              | components["schemas"]["AuditLogEventEnvironmentSettings"]
              | null;
          promotion_cleanup_strategy: string
          | null;
          ramp_up_duration_seconds: number | null;
          ramp_up_step_size: number | null;
          ramp_up_while_promoting: boolean | null;
          redeploy_on_promotion: boolean | null;
          replica_overhead_percent: number | null;
          request_backpressure_policy: string | null;
          rolling_deploy: boolean | null;
          rolling_deploy_strategy: string | null;
          scale_down_delay: number | null;
          schedules:
              | components["schemas"]["AuditLogEventAutoscalingScheduleChange"][]
              | null;
          stabilization_time_seconds: number
          | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AuditLogEventEnvironmentUpdatedV1

      A model environment's settings were updated.

      • autoscaling_window: number | null

        Autoscaling Window

      • concurrency_target: number

        Concurrency Target

      • deployment_type: string | null

        Deployment Type

      • environment_name: string

        Environment Name

      • event_type: "ENVIRONMENT_UPDATED"

        discriminator enum property added by openapi-typescript

      • max_replica: number

        Max Replica

      • max_scale_down_rate: number | null

        Max Scale Down Rate

      • max_surge_percent: number | null

        Max Surge Percent

      • max_unavailable_percent: number | null

        Max Unavailable Percent

      • min_replica: number

        Min Replica

      • model_id: string

        Model Id

      • model_name: string

        Model Name

      • previous_settings: components["schemas"]["AuditLogEventEnvironmentSettings"] | null
      • promotion_cleanup_strategy: string | null

        Promotion Cleanup Strategy

      • ramp_up_duration_seconds: number | null

        Ramp Up Duration Seconds

      • ramp_up_step_size: number | null

        Ramp Up Step Size

      • ramp_up_while_promoting: boolean | null

        Ramp Up While Promoting

      • redeploy_on_promotion: boolean | null

        Redeploy On Promotion

      • replica_overhead_percent: number | null

        Replica Overhead Percent

      • request_backpressure_policy: string | null

        Request Backpressure Policy

        null
        
      • rolling_deploy: boolean | null

        Rolling Deploy

      • rolling_deploy_strategy: string | null

        Rolling Deploy Strategy

      • scale_down_delay: number | null

        Scale Down Delay

      • schedules: components["schemas"]["AuditLogEventAutoscalingScheduleChange"][] | null

        Schedules

      • stabilization_time_seconds: number | null

        Stabilization Time Seconds

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

      • target_utilization_percentage: number | null

        Target Utilization Percentage

    • AuditLogEventGatewayEndpointCreated: {
          event_type: "GATEWAY_ENDPOINT_CREATED";
          gateway_endpoint_id: string;
          slug: string;
      }

      AuditLogEventGatewayEndpointCreatedV1

      A Frontier Gateway endpoint was created.

      • event_type: "GATEWAY_ENDPOINT_CREATED"

        discriminator enum property added by openapi-typescript

      • gateway_endpoint_id: string

        Gateway Endpoint Id

      • slug: string

        Slug

    • AuditLogEventGatewayEndpointDeleted: {
          event_type: "GATEWAY_ENDPOINT_DELETED";
          gateway_endpoint_id: string;
          slug: string;
      }

      AuditLogEventGatewayEndpointDeletedV1

      A Frontier Gateway endpoint was deleted.

      • event_type: "GATEWAY_ENDPOINT_DELETED"

        discriminator enum property added by openapi-typescript

      • gateway_endpoint_id: string

        Gateway Endpoint Id

      • slug: string

        Slug

    • AuditLogEventGatewayEndpointUpdated: {
          event_type: "GATEWAY_ENDPOINT_UPDATED";
          gateway_endpoint_id: string;
          previous_slug: string | null;
          slug: string;
      }

      AuditLogEventGatewayEndpointUpdatedV1

      A Frontier Gateway endpoint was updated.

      • event_type: "GATEWAY_ENDPOINT_UPDATED"

        discriminator enum property added by openapi-typescript

      • gateway_endpoint_id: string

        Gateway Endpoint Id

      • previous_slug: string | null

        Previous Slug

      • slug: string

        Slug

    • AuditLogEventModelDeleted: { event_type: "MODEL_DELETED"; model_id: string; model_name: string }

      AuditLogEventModelDeletedV1

      A model was deleted.

      • event_type: "MODEL_DELETED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventModelDeployed: {
          deployment_id: string;
          deployment_name: string;
          environment_name: string | null;
          event_type: "MODEL_DEPLOYED";
          model_id: string;
          model_name: string;
          publish: boolean;
          scale_previous_to_zero: boolean;
          trusted: boolean;
      }

      AuditLogEventModelDeployedV1

      A model deployment was created.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • environment_name: string | null

        Environment Name

      • event_type: "MODEL_DEPLOYED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

      • publish: boolean

        Publish

      • scale_previous_to_zero: boolean

        Scale Previous To Zero

      • trusted: boolean

        Trusted

    • AuditLogEventModelDeploymentActivated: {
          deployment_id: string;
          deployment_name: string;
          event_type: "MODEL_DEPLOYMENT_ACTIVATED";
          model_id: string;
          model_name: string;
      }

      AuditLogEventModelDeploymentActivatedV1

      A model deployment was activated.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • event_type: "MODEL_DEPLOYMENT_ACTIVATED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventModelDeploymentAutoscalingSettingsChanged: {
          autoscaling_window: number | null;
          concurrency_target: number;
          deployment_id: string;
          deployment_name: string;
          deployment_type: string | null;
          event_type: "MODEL_DEPLOYMENT_AUTOSCALING_SETTINGS_CHANGED";
          max_replica: number;
          max_scale_down_rate: number | null;
          min_replica: number;
          model_id: string;
          model_name: string;
          previous_settings:
              | components["schemas"]["AuditLogEventAutoscalingSettings"]
              | null;
          scale_down_delay: number
          | null;
          schedules:
              | components["schemas"]["AuditLogEventAutoscalingScheduleChange"][]
              | null;
          target_in_flight_tokens: number
          | null;
          target_utilization_percentage: number | null;
      }

      AuditLogEventModelDeploymentAutoscalingSettingsChangedV1

      A model deployment's autoscaling settings were changed.

      • autoscaling_window: number | null

        Autoscaling Window

      • concurrency_target: number

        Concurrency Target

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • deployment_type: string | null

        Deployment Type

      • event_type: "MODEL_DEPLOYMENT_AUTOSCALING_SETTINGS_CHANGED"

        discriminator enum property added by openapi-typescript

      • max_replica: number

        Max Replica

      • max_scale_down_rate: number | null

        Max Scale Down Rate

      • min_replica: number

        Min Replica

      • model_id: string

        Model Id

      • model_name: string

        Model Name

      • previous_settings: components["schemas"]["AuditLogEventAutoscalingSettings"] | null
      • scale_down_delay: number | null

        Scale Down Delay

      • schedules: components["schemas"]["AuditLogEventAutoscalingScheduleChange"][] | null

        Schedules

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

      • target_utilization_percentage: number | null

        Target Utilization Percentage

    • AuditLogEventModelDeploymentDeactivated: {
          deployment_id: string;
          deployment_name: string;
          event_type: "MODEL_DEPLOYMENT_DEACTIVATED";
          model_id: string;
          model_name: string;
      }

      AuditLogEventModelDeploymentDeactivatedV1

      A model deployment was deactivated.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • event_type: "MODEL_DEPLOYMENT_DEACTIVATED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventModelDeploymentDeleted: {
          deployment_id: string;
          deployment_name: string;
          event_type: "MODEL_DEPLOYMENT_DELETED";
          model_id: string;
          model_name: string;
      }

      AuditLogEventModelDeploymentDeletedV1

      A model deployment was deleted.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • event_type: "MODEL_DEPLOYMENT_DELETED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventModelDeploymentInstanceTypeChanged: {
          deployment_id: string;
          deployment_name: string;
          event_type: "MODEL_DEPLOYMENT_INSTANCE_TYPE_CHANGED";
          instance_type_name: string;
          model_id: string;
          model_name: string;
      }

      AuditLogEventModelDeploymentInstanceTypeChangedV1

      A model deployment's instance type was changed.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • event_type: "MODEL_DEPLOYMENT_INSTANCE_TYPE_CHANGED"

        discriminator enum property added by openapi-typescript

      • instance_type_name: string

        Instance Type Name

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventModelDeploymentPromoted: {
          deployment_id: string;
          deployment_name: string;
          environment_id: string | null;
          environment_name: string | null;
          event_type: "MODEL_DEPLOYMENT_PROMOTED";
          model_id: string;
          model_name: string;
      }

      AuditLogEventModelDeploymentPromotedV1

      A model deployment was promoted to an environment.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • environment_id: string | null

        Environment Id

      • environment_name: string | null

        Environment Name

      • event_type: "MODEL_DEPLOYMENT_PROMOTED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventModelDeploymentRequestBackpressureSettingsChanged: {
          deployment_id: string;
          deployment_name: string;
          event_type: "MODEL_DEPLOYMENT_REQUEST_BACKPRESSURE_SETTINGS_CHANGED";
          model_id: string;
          model_name: string;
          policy: string | null;
          previous_policy: string | null;
      }

      AuditLogEventModelDeploymentRequestBackpressureSettingsChangedV1

      A model deployment's request backpressure settings were changed.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • event_type: "MODEL_DEPLOYMENT_REQUEST_BACKPRESSURE_SETTINGS_CHANGED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

      • policy: string | null

        Policy

        null
        
      • previous_policy: string | null

        Previous Policy

        null
        
    • AuditLogEventModelDeploymentRetried: {
          deployment_id: string;
          deployment_name: string;
          event_type: "MODEL_DEPLOYMENT_RETRIED";
          model_id: string;
          model_name: string;
          retried: boolean;
      }

      AuditLogEventModelDeploymentRetriedV1

      A model deployment build was retried.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • event_type: "MODEL_DEPLOYMENT_RETRIED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

      • retried: boolean

        Retried

    • AuditLogEventModelPromotionControlAction: {
          action: components["schemas"]["AuditLogPromotionControlAction"];
          deployment_id: string;
          deployment_name: string;
          environment_id: string | null;
          environment_name: string;
          event_type: "MODEL_PROMOTION_CONTROL_ACTION";
          model_id: string;
          model_name: string;
      }

      AuditLogEventModelPromotionControlActionV1

      A user-initiated promotion control signal was sent to a rolling promotion.

      • action: components["schemas"]["AuditLogPromotionControlAction"]
      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • environment_id: string | null

        Environment Id

      • environment_name: string

        Environment Name

      • event_type: "MODEL_PROMOTION_CONTROL_ACTION"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

    • AuditLogEventReplicaTerminated: {
          deployment_id: string;
          deployment_name: string;
          event_type: "REPLICA_TERMINATED";
          model_id: string;
          model_name: string;
          replica_id: string;
      }

      AuditLogEventReplicaTerminatedV1

      A replica of a model deployment was terminated.

      • deployment_id: string

        Deployment Id

      • deployment_name: string

        Deployment Name

      • event_type: "REPLICA_TERMINATED"

        discriminator enum property added by openapi-typescript

      • model_id: string

        Model Id

      • model_name: string

        Model Name

      • replica_id: string

        Replica Id

    • AuditLogEventRequireGroupBasedAdminsEnabled: { event_type: "REQUIRE_GROUP_BASED_ADMINS_ENABLED"; organization_id: string }

      AuditLogEventRequireGroupBasedAdminsEnabledV1

      Group-based admin enforcement was enabled for the organization.

      • event_type: "REQUIRE_GROUP_BASED_ADMINS_ENABLED"

        discriminator enum property added by openapi-typescript

      • organization_id: string

        Organization Id

    • AuditLogEventSecretDeleted: { event_type: "SECRET_DELETED"; secret_id: string; secret_name: string }

      AuditLogEventSecretDeletedV1

      A secret was deleted.

      • event_type: "SECRET_DELETED"

        discriminator enum property added by openapi-typescript

      • secret_id: string

        Secret Id

      • secret_name: string

        Secret Name

    • AuditLogEventSecretUpdated: { event_type: "SECRET_UPDATED"; secret_id: string; secret_name: string }

      AuditLogEventSecretUpdatedV1

      A secret was created or updated.

      • event_type: "SECRET_UPDATED"

        discriminator enum property added by openapi-typescript

      • secret_id: string

        Secret Id

      • secret_name: string

        Secret Name

    • AuditLogEventSshCertificateSigned: {
          event_type: "SSH_CERTIFICATE_SIGNED";
          expires_at: string;
          project_id: string;
          proxy_address: string;
          replica_id: string;
          workload_id: string;
          workload_type: string;
      }

      AuditLogEventSshCertificateSignedV1

      An SSH certificate was signed for a workload.

      • event_type: "SSH_CERTIFICATE_SIGNED"

        discriminator enum property added by openapi-typescript

      • expires_at: string

        Expires At

      • project_id: string

        Project Id

      • proxy_address: string

        Proxy Address

      • replica_id: string

        Replica Id

      • workload_id: string

        Workload Id

      • workload_type: string

        Workload Type

    • AuditLogEventType:
          | "MODEL_DEPLOYED"
          | "MODEL_DEPLOYMENT_ACTIVATED"
          | "MODEL_DEPLOYMENT_DEACTIVATED"
          | "MODEL_DEPLOYMENT_RETRIED"
          | "MODEL_DEPLOYMENT_PROMOTED"
          | "MODEL_DEPLOYMENT_AUTOSCALING_SETTINGS_CHANGED"
          | "MODEL_DEPLOYMENT_REQUEST_BACKPRESSURE_SETTINGS_CHANGED"
          | "MODEL_DEPLOYMENT_INSTANCE_TYPE_CHANGED"
          | "MODEL_DEPLOYMENT_DELETED"
          | "MODEL_DELETED"
          | "CHAIN_DEPLOYED"
          | "CHAIN_DEPLOYMENT_ACTIVATED"
          | "CHAIN_DEPLOYMENT_DEACTIVATED"
          | "CHAIN_DEPLOYMENT_PROMOTED"
          | "CHAINLET_AUTOSCALING_SETTINGS_CHANGED"
          | "CHAINLET_INSTANCE_TYPE_CHANGED"
          | "CHAIN_DEPLOYMENT_DELETED"
          | "CHAIN_DELETED"
          | "CHAIN_ENVIRONMENT_CREATED"
          | "CHAIN_ENVIRONMENT_UPDATED"
          | "SECRET_UPDATED"
          | "SECRET_DELETED"
          | "API_KEY_CREATED"
          | "API_KEY_DELETED"
          | "GATEWAY_ENDPOINT_CREATED"
          | "GATEWAY_ENDPOINT_UPDATED"
          | "GATEWAY_ENDPOINT_DELETED"
          | "USER_INVITED"
          | "USER_JOINED_ORGANIZATION"
          | "WEBHOOK_SIGNING_SECRET_CREATED"
          | "WEBHOOK_SIGNING_SECRET_ROTATED"
          | "WEBHOOK_SIGNING_SECRET_DELETED"
          | "USER_ROLE_UPDATED"
          | "USER_TEAM_ROLE_UPDATED"
          | "USER_REMOVED"
          | "DIRECTORY_GROUP_ROLE_UPDATED"
          | "REQUIRE_GROUP_BASED_ADMINS_ENABLED"
          | "ENVIRONMENT_CREATED"
          | "ENVIRONMENT_UPDATED"
          | "ENVIRONMENT_DELETED"
          | "REPLICA_TERMINATED"
          | "MODEL_PROMOTION_CONTROL_ACTION"
          | "SSH_CERTIFICATE_SIGNED"
          | "VOLUME_DELETED"
          | "VOLUME_VERSION_DELETED"
          | "VOLUME_VERSION_RESTORED"

      AuditLogEventTypeV1

      Type of action recorded by an audit-log entry.

    • AuditLogEventTypeGroup:
          | "DEPLOYED"
          | "PROMOTED"
          | "ACTIVATED_DEACTIVATED"
          | "AUTOSCALING_SETTINGS"
          | "REQUEST_BACKPRESSURE_SETTINGS"
          | "INSTANCE_TYPE_CHANGED"
          | "ENVIRONMENT_SETTINGS"
          | "REPLICA_TERMINATED"
          | "DELETED"
          | "SECRETS"
          | "API_KEYS"
          | "GATEWAY"
          | "WEBHOOK_SIGNING_SECRETS"
          | "USER_MANAGEMENT"
          | "DIRECTORY_GROUP_MANAGEMENT"
          | "SSH"

      AuditLogEventTypeGroupV1

      Coarse grouping of event types, used to filter the audit log.

    • AuditLogEventUserInvited: { event_type: "USER_INVITED"; invited_user_email: string; role_name: string }

      AuditLogEventUserInvitedV1

      A user was invited to the organization.

      • event_type: "USER_INVITED"

        discriminator enum property added by openapi-typescript

      • invited_user_email: string

        Invited User Email

      • role_name: string

        Role Name

    • AuditLogEventUserJoinedOrganization: {
          event_type: "USER_JOINED_ORGANIZATION";
          new_user_email: string;
          user_id: string;
      }

      AuditLogEventUserJoinedOrganizationV1

      A user joined the organization.

      • event_type: "USER_JOINED_ORGANIZATION"

        discriminator enum property added by openapi-typescript

      • new_user_email: string

        New User Email

      • user_id: string

        User Id

    • AuditLogEventUserRemoved: { event_type: "USER_REMOVED"; removed_user_email: string }

      AuditLogEventUserRemovedV1

      A user was removed from the organization.

      • event_type: "USER_REMOVED"

        discriminator enum property added by openapi-typescript

      • removed_user_email: string

        Removed User Email

    • AuditLogEventUserRoleUpdated: {
          event_type: "USER_ROLE_UPDATED";
          new_role_name: string;
          user_email: string;
          user_id: string;
      }

      AuditLogEventUserRoleUpdatedV1

      A user's organization role was updated.

      • event_type: "USER_ROLE_UPDATED"

        discriminator enum property added by openapi-typescript

      • new_role_name: string

        New Role Name

      • user_email: string

        User Email

      • user_id: string

        User Id

    • AuditLogEventUserTeamRoleUpdated: {
          event_type: "USER_TEAM_ROLE_UPDATED";
          new_role_name: string;
          team_id: string;
          team_name: string;
          user_email: string;
          user_id: string;
      }

      AuditLogEventUserTeamRoleUpdatedV1

      A user's team role was updated.

      • event_type: "USER_TEAM_ROLE_UPDATED"

        discriminator enum property added by openapi-typescript

      • new_role_name: string

        New Role Name

      • team_id: string

        Team Id

      • team_name: string

        Team Name

      • user_email: string

        User Email

      • user_id: string

        User Id

    • AuditLogEventVolumeDeleted: {
          event_type: "VOLUME_DELETED";
          namespace: string;
          versions_deleted: number;
          volume_name: string;
          volume_ref: string;
      }

      AuditLogEventVolumeDeletedV1

      A volume was deleted, tombstoning every version it still held.

      • event_type: "VOLUME_DELETED"

        discriminator enum property added by openapi-typescript

      • namespace: string

        Namespace

      • versions_deleted: number

        Versions Deleted

      • volume_name: string

        Volume Name

      • volume_ref: string

        Volume Ref

    • AuditLogEventVolumeVersionDeleted: {
          digest: string;
          event_type: "VOLUME_VERSION_DELETED";
          namespace: string;
          version: string;
          volume_name: string;
          volume_ref: string;
      }

      AuditLogEventVolumeVersionDeletedV1

      One version of a volume was deleted.

      • digest: string

        Digest

      • event_type: "VOLUME_VERSION_DELETED"

        discriminator enum property added by openapi-typescript

      • namespace: string

        Namespace

      • version: string

        Version

      • volume_name: string

        Volume Name

      • volume_ref: string

        Volume Ref

    • AuditLogEventVolumeVersionRestored: {
          digest: string;
          event_type: "VOLUME_VERSION_RESTORED";
          namespace: string;
          version: string;
          volume_name: string;
          volume_ref: string;
      }

      AuditLogEventVolumeVersionRestoredV1

      A deleted version of a volume was restored.

      • digest: string

        Digest

      • event_type: "VOLUME_VERSION_RESTORED"

        discriminator enum property added by openapi-typescript

      • namespace: string

        Namespace

      • version: string

        Version

      • volume_name: string

        Volume Name

      • volume_ref: string

        Volume Ref

    • AuditLogEventWebhookSigningSecretCreated: {
          event_type: "WEBHOOK_SIGNING_SECRET_CREATED";
          webhook_signing_secret_id: string;
      }

      AuditLogEventWebhookSigningSecretCreatedV1

      A webhook signing secret was created.

      • event_type: "WEBHOOK_SIGNING_SECRET_CREATED"

        discriminator enum property added by openapi-typescript

      • webhook_signing_secret_id: string

        Webhook Signing Secret Id

    • AuditLogEventWebhookSigningSecretDeleted: {
          event_type: "WEBHOOK_SIGNING_SECRET_DELETED";
          webhook_signing_secret_id: string;
      }

      AuditLogEventWebhookSigningSecretDeletedV1

      A webhook signing secret was deleted.

      • event_type: "WEBHOOK_SIGNING_SECRET_DELETED"

        discriminator enum property added by openapi-typescript

      • webhook_signing_secret_id: string

        Webhook Signing Secret Id

    • AuditLogEventWebhookSigningSecretRotated: {
          event_type: "WEBHOOK_SIGNING_SECRET_ROTATED";
          webhook_signing_secret_id: string;
      }

      AuditLogEventWebhookSigningSecretRotatedV1

      A webhook signing secret was rotated.

      • event_type: "WEBHOOK_SIGNING_SECRET_ROTATED"

        discriminator enum property added by openapi-typescript

      • webhook_signing_secret_id: string

        Webhook Signing Secret Id

    • AuditLogPromotionControlAction: "PAUSE" | "RESUME" | "FORCE_CANCEL" | "FORCE_ROLL_FORWARD" | "GRACEFUL_CANCEL"

      AuditLogPromotionControlActionV1

      User-initiated promotion control signal recorded on a promotion-control event.

    • AuditLogSortDirection: "DESC" | "ASC"

      AuditLogSortDirectionV1

      Sort order of returned entries, by creation time.

    • AuditLogSource: "UI" | "API" | "MCP" | "SYSTEM" | "OTHER"

      AuditLogSourceV1

      Surface that issued the audited action.

    • AuthCode: {
          auth_code: string;
          auth_url: string;
          expires_at: string | null;
          generated_at: string | null;
          replica_id: string;
          session_id: string;
          tunnel_name: string | null;
          working_directory: string | null;
      }

      AuthCodeV1

      Authentication code for a training job interactive session node.

      • auth_code: string

        Auth Code

        The device authentication code (e.g., '4F64-C0D9').

      • auth_url: string

        Auth Url

        URL where the user should enter the auth code (e.g., 'https://github.com/login/device').

      • expires_at: string | null

        Expires At

        When the session expires, in ISO 8601 format.

        null
        
      • generated_at: string | null

        Generated At

        When the auth code was generated, in ISO 8601 format.

        null
        
      • replica_id: string

        Replica Id

        Replica identifier in gXXrY format (e.g., 'g00r0' for group 0, replica 0).

      • session_id: string

        Session Id

        Unique identifier of the interactive session.

      • tunnel_name: string | null

        Tunnel Name

        The name of the tunnel node.

        null
        
      • working_directory: string | null

        Working Directory

        The working directory of the session.

        null
        
    • AuthMethod: "CUSTOM_SECRET" | "AWS_OIDC" | "GCP_OIDC" | "AWS_ASSUME_ROLE"

      AuthMethod

    • AutoscalingSchedule: {
          autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"];
          cadence: "DAILY" | "HOURLY";
          enabled: boolean;
          end_hour: number | null;
          end_minute: number;
          id: string;
          name: string;
          start_hour: number | null;
          start_minute: number;
          weekdays: components["schemas"]["AutoscalingScheduleWeekday"][];
      }

      AutoscalingScheduleV1

      • autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"]

        Raw autoscaling overrides applied during the schedule window

      • cadence: "DAILY" | "HOURLY"

        Cadence of the schedule. DAILY runs once per selected weekday; HOURLY repeats the minute window every hour on selected weekdays. (enum property replaced by openapi-typescript)

      • enabled: boolean

        Enabled

        Whether the schedule is enabled

      • end_hour: number | null

        End Hour

        End hour in the environment schedule timezone. Omitted for unrestricted HOURLY schedules.

        null
        
      • end_minute: number

        End Minute

        End minute of the schedule window

      • id: string

        Id

        Stable unique identifier of the schedule

      • name: string

        Name

        Name of the schedule

      • start_hour: number | null

        Start Hour

        Start hour in the environment schedule timezone. Omitted for unrestricted HOURLY schedules.

        null
        
      • start_minute: number

        Start Minute

        Start minute of the schedule window

      • weekdays: components["schemas"]["AutoscalingScheduleWeekday"][]

        Weekdays

        Weekdays on which the schedule runs

    • AutoscalingScheduleSettings: {
          autoscaling_window: number | null;
          concurrency_target: number | null;
          max_replica: number;
          max_scale_down_rate: number | null;
          min_replica: number;
          scale_down_delay: number | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AutoscalingScheduleSettingsV1

      • autoscaling_window: number | null

        Autoscaling Window

        Timeframe of traffic considered for autoscaling decisions. Null inherits the environment value.

      • concurrency_target: number | null

        Concurrency Target

        Number of requests per replica before scaling up. Null inherits the environment value.

      • max_replica: number

        Max Replica

        Maximum number of replicas

      • max_scale_down_rate: number | null

        Max Scale Down Rate

        Maximum percentage of replicas that can be removed per autoscaling window. Null inherits the environment value.

      • min_replica: number

        Min Replica

        Minimum number of replicas

      • scale_down_delay: number | null

        Scale Down Delay

        Waiting period before scaling down any active replica. Null inherits the environment value.

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

        Target number of in-flight tokens for autoscaling decisions. Null inherits the environment value. Early access only.

      • target_utilization_percentage: number | null

        Target Utilization Percentage

        Target utilization percentage for scaling up/down. Null inherits the environment value.

    • AutoscalingScheduleSettingsRequest: {
          autoscaling_window: number | null;
          concurrency_target: number | null;
          max_replica: number;
          max_scale_down_rate: number | null;
          min_replica: number;
          scale_down_delay: number | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AutoscalingScheduleSettingsRequestV1

      A complete set of raw autoscaling overrides for a schedule.

      • autoscaling_window: number | null

        Autoscaling Window

        Timeframe of traffic considered for autoscaling decisions. Null stores no schedule override and follows the current environment value.

      • concurrency_target: number | null

        Concurrency Target

        Number of requests per replica before scaling up. Null stores no schedule override and follows the current environment value.

      • max_replica: number

        Max Replica

        Maximum number of replicas

      • max_scale_down_rate: number | null

        Max Scale Down Rate

        Maximum percentage of replicas that can be removed per autoscaling window. Null stores no schedule override and follows the current environment value.

      • min_replica: number

        Min Replica

        Minimum number of replicas

      • scale_down_delay: number | null

        Scale Down Delay

        Waiting period before scaling down any active replica. Null stores no schedule override and follows the current environment value.

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

        Target number of in-flight tokens for autoscaling decisions. Null stores no schedule override and follows the current environment value. Early access only.

      • target_utilization_percentage: number | null

        Target Utilization Percentage

        Target utilization percentage for scaling up/down. Null stores no schedule override and follows the current environment value.

    • AutoscalingScheduleState: {
          autoscaling_settings: components["schemas"]["AutoscalingSettings"];
          schedule_id: string | null;
      }

      AutoscalingScheduleStateV1

      • autoscaling_settings: components["schemas"]["AutoscalingSettings"]

        Autoscaling settings on the current serving deployment. In a PATCH response, this snapshot can precede asynchronous schedule reconciliation; poll the GET endpoint for the applied state.

      • schedule_id: string | null

        Schedule Id

        Stable schedule identifier, or null when the baseline settings apply

    • AutoscalingScheduleUpsert: {
          autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"];
          cadence: "DAILY" | "HOURLY";
          enabled: boolean;
          end_hour?: number | null;
          end_minute: number;
          id?: string | null;
          name: string;
          start_hour?: number | null;
          start_minute: number;
          weekdays: components["schemas"]["AutoscalingScheduleWeekday"][];
      }

      AutoscalingScheduleUpsertV1

      A complete recurring schedule submitted for create or replacement.

      • autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"]

        Complete raw autoscaling overrides for the schedule. Every field is required; nullable fields store no schedule override and follow the current environment value.

      • cadence: "DAILY" | "HOURLY"

        Recurring schedule cadence (enum property replaced by openapi-typescript)

      • enabled: boolean

        Enabled

        Whether the schedule is enabled

      • Optionalend_hour?: number | null

        End Hour

        End hour in the environment schedule timezone. Omit for unrestricted HOURLY schedules.

      • end_minute: number

        End Minute

        End minute of the schedule window

      • Optionalid?: string | null

        Id

        Stable schedule identifier. Omit this field to create a schedule.

      • name: string

        Name

        Name of the schedule

      • Optionalstart_hour?: number | null

        Start Hour

        Start hour in the environment schedule timezone. Omit for unrestricted HOURLY schedules.

      • start_minute: number

        Start Minute

        Start minute of the schedule window

      • weekdays: components["schemas"]["AutoscalingScheduleWeekday"][]

        Weekdays

        Weekdays on which the schedule runs

    • AutoscalingScheduleWeekday:
          | "SUNDAY"
          | "MONDAY"
          | "TUESDAY"
          | "WEDNESDAY"
          | "THURSDAY"
          | "FRIDAY"
          | "SATURDAY"

      AutoscalingScheduleWeekdayV1

    • AutoscalingSettings: {
          autoscaling_window: number | null;
          concurrency_target: number;
          max_replica: number;
          max_scale_down_rate: number | null;
          min_replica: number;
          scale_down_delay: number | null;
          target_in_flight_tokens: number | null;
          target_utilization_percentage: number | null;
      }

      AutoscalingSettingsV1

      Autoscaling settings for a deployment.

      • autoscaling_window: number | null

        Autoscaling Window

        Timeframe of traffic considered for autoscaling decisions

      • concurrency_target: number

        Concurrency Target

        Number of requests per replica before scaling up

      • max_replica: number

        Max Replica

        Maximum number of replicas

      • max_scale_down_rate: number | null

        Max Scale Down Rate

        Maximum percentage of replicas that can be removed per autoscaling window (1–50). E.g. 20 means at most 20% of replicas are removed per window.

        null
        
      • min_replica: number

        Min Replica

        Minimum number of replicas

      • scale_down_delay: number | null

        Scale Down Delay

        Waiting period before scaling down any active replica

      • target_in_flight_tokens: number | null

        Target In Flight Tokens

        Target number of in-flight tokens for autoscaling decisions. Early access only.

        null
        
      • target_utilization_percentage: number | null

        Target Utilization Percentage

        Target utilization percentage for scaling up/down.

    • AwsAssumeRole: { baseten_role_arn: string; external_id: string }

      AwsAssumeRoleV1

      AWS AssumeRole trust-policy inputs for the organization.

      • baseten_role_arn: string

        Baseten Role Arn

        Baseten role ARN to allow in an IAM role's trust policy

      • external_id: string

        External Id

        sts:ExternalId Baseten presents when assuming the role

    • AwsAssumeRoleDockerAuth: { region: string; role_arn: string }

      AwsAssumeRoleDockerAuthV1

      AWS assume-role details for the registry.

      • region: string

        Region

        AWS region of the registry

      • role_arn: string

        Role Arn

        AWS IAM role ARN that Baseten assumes to pull from the registry. The role's trust policy must allow Baseten's AWS principal with your Baseten-provided external ID.

    • AWSCredentials: {
          aws_access_key_id: string;
          aws_secret_access_key: string;
          aws_session_token: string;
      }

      AWSCredentialsV1

      AWS credentials

      • aws_access_key_id: string

        Aws Access Key Id

        The AWS access key ID

      • aws_secret_access_key: string

        Aws Secret Access Key

        The AWS secret access key

      • aws_session_token: string

        Aws Session Token

        The AWS session token

    • AwsIamDockerAuth: {
          access_key_secret_ref: components["schemas"]["SecretReference"];
          secret_access_key_secret_ref: components["schemas"]["SecretReference"];
      }

      AwsIamDockerAuthV1

      AWS details for the registry.

      • access_key_secret_ref: components["schemas"]["SecretReference"]

        Name of the access key secret

      • secret_access_key_secret_ref: components["schemas"]["SecretReference"]

        Name of the secret key secret

    • AwsOidcDockerAuth: { region: string; role_arn: string }

      AwsOidcDockerAuthV1

      AWS OIDC details for the registry.

      • region: string

        Region

        AWS region for OIDC authentication

      • role_arn: string

        Role Arn

        AWS IAM role ARN for OIDC authentication

    • BasetenLatestCheckpointConfig: {
          job_id?: string | null;
          project_name?: string | null;
          typ: "baseten_latest_checkpoint";
      }

      BasetenLatestCheckpointConfig

      • Optionaljob_id?: string | null

        Job Id

        ID of the job to load the checkpoint from

      • Optionalproject_name?: string | null

        Project Name

        Name of the project to load the checkpoint from

      • typ: "baseten_latest_checkpoint"

        discriminator enum property added by openapi-typescript

    • BasetenNamedCheckpointConfig: {
          checkpoint_name: string;
          job_id?: string | null;
          project_name?: string | null;
          typ: "baseten_named_checkpoint";
      }

      BasetenNamedCheckpointConfig

      • checkpoint_name: string

        Checkpoint Name

        Name of the checkpoint to load from

      • Optionaljob_id?: string | null

        Job Id

        ID of the job to load the checkpoint from

      • Optionalproject_name?: string | null

        Project Name

        Name of the project to load the checkpoint from

      • typ: "baseten_named_checkpoint"

        discriminator enum property added by openapi-typescript

    • BenchmarkSnapshot: {
          embedding?: components["schemas"]["EmbeddingBenchmarkMetrics"] | null;
          llm?: components["schemas"]["LLMBenchmarkMetrics"] | null;
          measured_at: string;
          profile?: string | null;
          replicas?: number | null;
          run_id: string;
          tts?: components["schemas"]["TTSBenchmarkMetrics"] | null;
      }

      BenchmarkSnapshotV1

      • Optionalembedding?: components["schemas"]["EmbeddingBenchmarkMetrics"] | null
      • Optionalllm?: components["schemas"]["LLMBenchmarkMetrics"] | null
      • measured_at: string

        Measured At Format: date

      • Optionalprofile?: string | null

        Profile

      • Optionalreplicas?: number | null

        Replicas

      • run_id: string

        Run Id

      • Optionaltts?: components["schemas"]["TTSBenchmarkMetrics"] | null
    • BillableResource: {
          base_model: string | null;
          chain_metadata: components["schemas"]["ChainMetadata"] | null;
          environment_name: string | null;
          id: string;
          instance_type: string | null;
          is_deleted: boolean;
          kind: components["schemas"]["ResourceKind"];
          model_id: string | null;
          model_name: string | null;
          name: string | null;
          team_id: string | null;
          team_name: string | null;
      }

      BillableResourceV1

      • base_model: string | null

        Base Model

        Base model used by this Loops trainer or sampler

        null
        
      • chain_metadata: components["schemas"]["ChainMetadata"] | null

        Chain metadata if this is a chainlet deployment

        null
        
      • environment_name: string | null

        Environment Name

        Environment name (e.g., 'production', 'staging')

        null
        
      • id: string

        Id

        Unique identifier of the resource

      • instance_type: string | null

        Instance Type

        Instance type used

        null
        
      • is_deleted: boolean

        Is Deleted

        Indicates if the resource has been deleted

      • kind: components["schemas"]["ResourceKind"]

        Resource kind (MODEL_DEPLOYMENT, CHAINLET, TRAINING_JOB, LOOPS_TRAINER, or LOOPS_SAMPLER)

      • model_id: string | null

        Model Id

        Unique identifier of the parent model for model deployments and chainlets

        null
        
      • model_name: string | null

        Model Name

        Name of the parent resource (e.g., model name for model deployments, training project name for training jobs)

        null
        
      • name: string | null

        Name

        Name of the resource

        null
        
      • team_id: string | null

        Team Id

        Unique identifier of the team that owns the resource. Only present for organizations with multiple teams enabled.

        null
        
      • team_name: string | null

        Team Name

        Name of the team that owns the resource. Only present for organizations with multiple teams enabled.

        null
        
    • BucketWidth: "1m" | "1h" | "1d"

      BucketWidth

    • CancelPromotionResponse: { message: string; status: components["schemas"]["CancelPromotionStatus"] }

      CancelPromotionResponseV1

      The response to a request to cancel a promotion.

      • message: string

        Message

        A message describing the status of the request to cancel a promotion

      • status: components["schemas"]["CancelPromotionStatus"]

        Status of the request to cancel a promotion. Can be CANCELED or RAMPING_DOWN.

    • CancelPromotionStatus: "CANCELED" | "RAMPING_DOWN"

      CancelPromotionStatusV1

      The status of a request to cancel a promotion.

    • CapacityAtSubmit: {
          gpu_type: string;
          last_modified: string;
          max_gpus: number;
          min_gpus: number | null;
      }

      CapacityAtSubmitV1

      A GPU capacity row as it stands now, with last_modified so callers can judge whether the value matches what the dequeue gate saw at submit time. Capacity rows are not historicized: edits overwrite in place. Compare last_modified against the response's submitted_at — if it's later, the value may have changed.

      • gpu_type: string

        Gpu Type

        GPU type identifier (e.g. H100, A100-40GB)

      • last_modified: string

        Last Modified Format: date-time

        When the capacity row was last modified

      • max_gpus: number

        Max Gpus

        Current max concurrent GPUs of this type

      • min_gpus: number | null

        Min Gpus

        Current baseline GPU allocation, if configured

        null
        
    • Chain: {
          created_at: string;
          deployments_count: number;
          id: string;
          name: string;
          team_name: string;
      }

      ChainV1

      A chain.

      • created_at: string

        Created At Format: date-time

        Time the chain was created in ISO 8601 format

      • deployments_count: number

        Deployments Count

        Number of deployments of the chain

      • id: string

        Id

        Unique identifier of the chain

      • name: string

        Name

        Name of the chain

      • team_name: string

        Team Name

        Name of the team associated with the chain

    • ChainDeployment: {
          chain_id: string;
          chainlets: components["schemas"]["Chainlet"][];
          created_at: string;
          environment: string | null;
          id: string;
          status: components["schemas"]["DeploymentStatus"];
      }

      ChainDeploymentV1

      A deployment of a chain.

      • chain_id: string

        Chain Id

        Unique identifier of the chain

      • chainlets: components["schemas"]["Chainlet"][]

        Chainlets

        Chainlets in the chain deployment

      • created_at: string

        Created At Format: date-time

        Time the chain deployment was created in ISO 8601 format

      • environment: string | null

        Environment

        Environment the chain deployment is deployed in

      • id: string

        Id

        Unique identifier of the chain deployment

      • status: components["schemas"]["DeploymentStatus"]

        Status of the chain deployment

    • ChainDeployments: { deployments: components["schemas"]["ChainDeployment"][] }

      ChainDeploymentsV1

      A list of chain deployments.

      • deployments: components["schemas"]["ChainDeployment"][]

        Deployments

        A list of chain deployments

    • ChainDeploymentTombstone: { chain_id: string; deleted: boolean; id: string }

      ChainDeploymentTombstoneV1

      A chain deployment tombstone.

      • chain_id: string

        Chain Id

        Unique identifier of the chain

      • deleted: boolean

        Deleted

        Whether the chain deployment was deleted

      • id: string

        Id

        Unique identifier of the chain deployment

    • ChainEnvironment: {
          candidate_deployment: components["schemas"]["ChainDeployment"] | null;
          chain_id: string;
          chainlet_settings: components["schemas"]["ChainletEnvironmentSettings"][];
          created_at: string;
          current_deployment: components["schemas"]["ChainDeployment"] | null;
          name: string;
          promotion_settings: components["schemas"]["PromotionSettings"];
      }

      ChainEnvironmentV1

      Environment for oracles.

      • candidate_deployment: components["schemas"]["ChainDeployment"] | null

        Candidate chain deployment being promoted to the environment, if a promotion is in progress

        null
        
      • chain_id: string

        Chain Id

        Unique identifier of the chain

      • chainlet_settings: components["schemas"]["ChainletEnvironmentSettings"][]

        Chainlet Settings

        Environment settings for the chainlets

      • created_at: string

        Created At Format: date-time

        Time the environment was created in ISO 8601 format

      • current_deployment: components["schemas"]["ChainDeployment"] | null

        Current chain deployment of the environment

      • name: string

        Name

        Name of the environment

      • promotion_settings: components["schemas"]["PromotionSettings"]

        Promotion settings for the environment

    • Chainlet: {
          active_replica_count: number;
          autoscaling_settings: components["schemas"]["AutoscalingSettings"] | null;
          id: string;
          instance_type_name: string;
          name: string;
          status: components["schemas"]["DeploymentStatus"];
      }

      ChainletV1

      A chainlet in a chain deployment.

      • active_replica_count: number

        Active Replica Count

        Number of active replicas

      • autoscaling_settings: components["schemas"]["AutoscalingSettings"] | null

        Autoscaling settings for the chainlet. If null, it has not finished deploying

      • id: string

        Id

        Unique identifier of the chainlet

      • instance_type_name: string

        Instance Type Name

        Name of the instance type the chainlet is deployed on

      • name: string

        Name

        Name of the chainlet

      • status: components["schemas"]["DeploymentStatus"]

        Status of the chainlet

    • ChainletEnvironmentAutoscalingSettingsUpdate: {
          autoscaling_settings: components["schemas"]["UpdateAutoscalingSettings"];
          chainlet_name: string;
      }

      ChainletEnvironmentAutoscalingSettingsUpdateV1

      The request to update the autoscaling settings for a chainlet.

      • autoscaling_settings: components["schemas"]["UpdateAutoscalingSettings"]

        Autoscaling settings for the chainlet

        {
        * "autoscaling_window": 800,
        * "concurrency_target": 3,
        * "max_replica": 2,
        * "max_scale_down_rate": null,
        * "min_replica": 1,
        * "scale_down_delay": 60,
        * "target_in_flight_tokens": null,
        * "target_utilization_percentage": null
        * }
      • chainlet_name: string

        Chainlet Name

        Name of the chainlet

        HelloWorld
        
    • ChainletEnvironmentInstanceTypeUpdate: { chainlet_name: string; instance_type_id: string }

      ChainletEnvironmentInstanceTypeUpdateV1

      A request to update the environment settings for a chainlet.

      • chainlet_name: string

        Chainlet Name

        Name of the chainlet

        HelloWorld
        
      • instance_type_id: string

        Instance Type Id

        Key of the instance type to use for the chainlet

        1x4
        
        2x8
        
        A10G:2x24x96
        
    • ChainletEnvironmentSettings: {
          autoscaling_settings:
              | components["schemas"]["AutoscalingSettings"]
              | null;
          chainlet_name: string;
          instance_type: components["schemas"]["InstanceType"];
      }

      ChainletEnvironmentSettingsV1

      Environment settings for a chainlet.

      • autoscaling_settings: components["schemas"]["AutoscalingSettings"] | null

        Autoscaling settings for the chainlet. If null, it has not finished deploying

      • chainlet_name: string

        Chainlet Name

        Name of the chainlet

      • instance_type: components["schemas"]["InstanceType"]

        Instance type for the chainlet

    • ChainletEnvironmentSettingsRequest: {
          autoscaling_settings?:
              | components["schemas"]["UpdateAutoscalingSettings"]
              | null;
          chainlet_name: string;
          instance_type_id?: string;
      }

      ChainletEnvironmentSettingsRequestV1

      Request to create environment settings for a chainlet.

      • Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | null

        Autoscaling settings for the chainlet

        {
        * "autoscaling_window": 60,
        * "concurrency_target": 1,
        * "max_replica": 1,
        * "max_scale_down_rate": null,
        * "min_replica": 0,
        * "scale_down_delay": 900,
        * "target_in_flight_tokens": null,
        * "target_utilization_percentage": 70
        * }
      • chainlet_name: string

        Chainlet Name

        Name of the chainlet

        HelloWorld
        
      • Optionalinstance_type_id?: string

        Instance Type Id

        ID of the instance type to use for the chainlet

        1x4
        
        2x8
        
        A10G:2x24x96
        
        H100:2x52x468
        
    • ChainMetadata: { chain_deployment_id: string; chain_id: string; chain_name: string | null }

      ChainMetadataV1

      • chain_deployment_id: string

        Chain Deployment Id

        Unique identifier of the chain deployment

      • chain_id: string

        Chain Id

        Unique identifier of the chain

      • chain_name: string | null

        Chain Name

        Name of the chain

        null
        
    • Chains: { chains: components["schemas"]["Chain"][] }

      ChainsV1

      A list of chains.

    • ChainTombstone: { deleted: boolean; id: string }

      ChainTombstoneV1

      A chain tombstone.

      • deleted: boolean

        Deleted

        Whether the chain was deleted

      • id: string

        Id

        Unique identifier of the chain

    • CheckpointFile: {
          last_modified: string;
          node_rank: number;
          relative_file_name: string;
          size_bytes: number;
          url: string;
      }

      CheckpointFile

      • last_modified: string

        Last Modified

      • node_rank: number

        Node Rank

      • relative_file_name: string

        Relative File Name

      • size_bytes: number

        Size Bytes

      • url: string

        Url

    • CheckpointSyncStatus: "SYNCING" | "COMPLETED"

      CheckpointSyncStatus

      Lifecycle state for the checkpoint uploader.

    • CreateApiKeyForGroupRequest: { name?: string | null }

      CreateApiKeyForGroupRequestV1

      • Optionalname?: string | null

        Name

        Optional display name for the new key.

        prod-key-1
        
    • CreateApiKeyForGroupResponse: { api_key: string; name: string | null; prefix: string }

      CreateApiKeyForGroupResponseV1

      • api_key: string

        Api Key

        Plaintext key string, returned exactly once.

      • name: string | null

        Name

        Display name of the key.

        null
        
      • prefix: string

        Prefix

        Key prefix (the part before the dot).

    • CreateAPIKeyRequest: {
          model_ids?: string[] | null;
          name?: string | null;
          team_id?: string | null;
          type: components["schemas"]["APIKeyCategory"];
      }

      CreateAPIKeyRequestV1

      Request to create an API key.

      • Optionalmodel_ids?: string[] | null

        Model Ids

        List of model IDs to scope the API key to, only present if type is 'WORKSPACE_EXPORT_METRICS' or 'WORKSPACE_INVOKE'

        [
        "aaaaaaaa"
        ]
      • Optionalname?: string | null

        Name

        Optional name for the API key

        my-api-key
        
      • Optionalteam_id?: string | null

        Team Id

        Team ID for a team-scoped key. When omitted, uses the team in the URL if present, otherwise your organization's default team. Must match the URL team when both are provided. Not supported for PERSONAL or WORKSPACE_MANAGE_API_KEYS keys.

      • type: components["schemas"]["APIKeyCategory"]

        Type of the API key.

        PERSONAL
        
        ROUTES
        
        WORKSPACE_MANAGE_API_KEYS
        
        WORKSPACE_EXPORT_METRICS
        
        WORKSPACE_INVOKE
        
        WORKSPACE_MANAGE_ALL
        
    • CreateChainEnvironmentRequest: {
          chainlet_settings?:
              | components["schemas"]["ChainletEnvironmentSettingsRequest"][]
              | null;
          name: string;
          promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
          | null;
      }

      CreateChainEnvironmentRequestV1

      A request to create a custom environment for a chain.

      • Optionalchainlet_settings?: components["schemas"]["ChainletEnvironmentSettingsRequest"][] | null

        Chainlet Settings

        Mapping of chainlet name to the desired chainlet environment settings

        [
        {
        "autoscaling_settings": {
        "autoscaling_window": 800,
        "concurrency_target": 4,
        "max_replica": 3,
        "max_scale_down_rate": null,
        "min_replica": 2,
        "scale_down_delay": 63,
        "target_in_flight_tokens": null,
        "target_utilization_percentage": null
        },
        "chainlet_name": "HelloWorld",
        "instance_type_id": "2x8"
        },
        {
        "autoscaling_settings": {
        "autoscaling_window": null,
        "concurrency_target": null,
        "max_replica": 3,
        "max_scale_down_rate": null,
        "min_replica": 3,
        "scale_down_delay": null,
        "target_in_flight_tokens": null,
        "target_utilization_percentage": null
        },
        "chainlet_name": "RandInt",
        "instance_type_id": "A10Gx8x32"
        }
        ]
      • name: string

        Name

        Name of the environment

        staging
        
      • Optionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | null

        Promotion settings for the environment

        {
        * "promotion_cleanup_strategy": null,
        * "ramp_up_duration_seconds": 600,
        * "ramp_up_while_promoting": true,
        * "redeploy_on_promotion": true,
        * "rolling_deploy": null,
        * "rolling_deploy_config": null
        * }
    • CreateDeploymentPatchRequest: {
          next_patch_point: components["schemas"]["DeploymentPatchPoint"];
          patch_ops: (
              | components["schemas"]["DeploymentPatchOpModelCode"]
              | components["schemas"]["DeploymentPatchOpPackage"]
              | components["schemas"]["DeploymentPatchOpConfig"]
              | components["schemas"]["DeploymentPatchOpPythonRequirement"]
              | components["schemas"]["DeploymentPatchOpEnvVar"]
              | components["schemas"]["DeploymentPatchOpExternalData"]
          )[];
          prev_patch_hash: string;
      }

      CreateDeploymentPatchRequestV1

      A patch to stage against the development deployment.

      Staging is durable on its own: the patch is persisted independently of the
      later sync, so a failed sync does not lose it.
      
      • next_patch_point: components["schemas"]["DeploymentPatchPoint"]

        The source state after this patch. The server derives its content hash from content_hashes.

      • patch_ops: (
            | components["schemas"]["DeploymentPatchOpModelCode"]
            | components["schemas"]["DeploymentPatchOpPackage"]
            | components["schemas"]["DeploymentPatchOpConfig"]
            | components["schemas"]["DeploymentPatchOpPythonRequirement"]
            | components["schemas"]["DeploymentPatchOpEnvVar"]
            | components["schemas"]["DeploymentPatchOpExternalData"]
        )[]

        Patch Ops

        The ordered ops that make up this patch. At least one op is required; a patch that changes nothing is not a valid request. There is no op for a directory: a directory comes into existence when the first file under it is added, and is removed when its last file is removed, so directory creation and deletion happen implicitly through the file ops. Adding or removing an otherwise empty directory therefore produces no ops even though it changes the source hash; do not send a patch request for such a change.

      • prev_patch_hash: string

        Prev Patch Hash

        Content hash of the patch point this patch is applied on - the link the staged patch must build on. A stale value (the base moved underneath the client) is rejected with a conflict.

    • CreateDeploymentPatchResponse: { patch_point: components["schemas"]["DeploymentPatchPointWithHash"] }

      CreateDeploymentPatchResponseV1

      The created patch, represented by the patch point it produced.

      • patch_point: components["schemas"]["DeploymentPatchPointWithHash"]

        The resulting patch point the staged patch produced; matches the pending point a subsequent state read returns.

    • CreatedModelDeployment: {
          deployment: components["schemas"]["Deployment"];
          model: components["schemas"]["Model"];
      }

      CreatedModelDeploymentV1

      A newly created deployment and its model.

      • deployment: components["schemas"]["Deployment"]

        The newly created deployment.

      • model: components["schemas"]["Model"]

        The model the deployment belongs to. May have been created by this call.

    • CreateEndpointRequest: {
          region?: components["schemas"]["SharedEndpointRegion"];
          slug: string;
          targets: components["schemas"]["EndpointTargetRequest"][];
      }

      CreateEndpointRequestV1

      • Optionalregion?: components["schemas"]["SharedEndpointRegion"]

        Region the new routing serves.

      • slug: string

        Slug

        Globally-unique slug of the form '{org_prefix}/{name}'.

        baseten/mymodel-4
        
      • targets: components["schemas"]["EndpointTargetRequest"][]

        Targets

        The endpoint's upstream targets. Exactly one target is supported at this time.

        [
        {
        "environment_name": "staging",
        "model_id": "3kZ9xqd",
        "provider": "BASETEN",
        "target_model": "custom/model-name"
        }
        ]
        [
        {
        "provider": "OPENAI",
        "secret_id": "3kZ9xqd",
        "target_model": "gpt-4o"
        }
        ]
        [
        {
        "base_url": "https://my-vllm.example.com",
        "provider": "OPENAI_COMPATIBLE",
        "secret_id": "3kZ9xqd",
        "target_model": "my-model"
        }
        ]
    • CreateEnvironmentRequest: {
          autoscaling_settings?:
              | components["schemas"]["UpdateAutoscalingSettings"]
              | null;
          name: string;
          promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
          | null;
          request_backpressure_settings?: | components["schemas"]["UpdateRequestBackpressureSettings"]
          | null;
      }

      CreateEnvironmentRequestV1

      A request to create an environment.

      • Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | null

        Autoscaling settings for the environment

        {
        * "autoscaling_window": 800,
        * "concurrency_target": 3,
        * "max_replica": 2,
        * "max_scale_down_rate": null,
        * "min_replica": 1,
        * "scale_down_delay": 60,
        * "target_in_flight_tokens": null,
        * "target_utilization_percentage": null
        * }
      • name: string

        Name

        Name of the environment

        staging
        
      • Optionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | null

        Promotion settings for the environment

        {
        * "promotion_cleanup_strategy": null,
        * "ramp_up_duration_seconds": 600,
        * "ramp_up_while_promoting": true,
        * "redeploy_on_promotion": true,
        * "rolling_deploy": true,
        * "rolling_deploy_config": null
        * }
      • Optionalrequest_backpressure_settings?: components["schemas"]["UpdateRequestBackpressureSettings"] | null

        Request backpressure settings for the environment.

    • CreateGroupHierarchy: {
          limit_enforcement?: components["schemas"]["LimitEnforcement"] | null;
          parent_group_id?: string | null;
      }

      CreateGroupHierarchyV1

      • Optionallimit_enforcement?: components["schemas"]["LimitEnforcement"] | null

        Limit behavior. Child groups inherit their parent's behavior when omitted; root groups default to Independent for backwards compatibility.

        INDEPENDENT
        
      • Optionalparent_group_id?: string | null

        Parent Group Id

        abc123
        
    • CreateGroupRequest: {
          hierarchy: components["schemas"]["CreateGroupHierarchy"];
          metadata: components["schemas"]["GroupMetadata"];
          models: components["schemas"]["ModelConfig"][];
      }

      CreateGroupRequestV1

      • hierarchy: components["schemas"]["CreateGroupHierarchy"]

        Parent linkage and limit enforcement mode. Immutable after creation.

      • metadata: components["schemas"]["GroupMetadata"]

        Group identity + display metadata.

      • models: components["schemas"]["ModelConfig"][]

        Models

        Per-model rate and usage limit configuration. Defines the group's complete model set. Must be non-empty.

        [
        {
        "slug": "my-org/claude"
        }
        ]
    • CreateJobWeightConfig: {
          allow_patterns?: string[] | null;
          auth?: components["schemas"]["TrainingWeightAuth"] | null;
          auth_secret_name?: string | null;
          ignore_patterns?: string[] | null;
          mount_location: string;
          source: string;
      }

      CreateJobWeightConfigV1

      Weight source configuration for MDN (Model Distribution Network).

      Enables training jobs to mount external model weights from HuggingFace, S3, GCS, R2,
      or CoreWeave via MDN's caching and CSI mounting infrastructure. Weights are mirrored
      once and deduplicated across training jobs.
      
      • Optionalallow_patterns?: string[] | null

        Allow Patterns

        File patterns to include (Unix-style shell patterns)

        [
        "*.safetensors",
        "config.json"
        ]
      • Optionalauth?: components["schemas"]["TrainingWeightAuth"] | null

        Authentication configuration for the weight source.

        {
        * "auth_method": "CUSTOM_SECRET",
        * "auth_secret_name": "hf_token"
        * }
        {
        * "auth_method": "AWS_OIDC",
        * "aws_oidc_region": "us-east-1",
        * "aws_oidc_role_arn": "arn:aws:iam::123456789012:role/weights-access"
        * }
        {
        * "auth_method": "GCP_OIDC",
        * "gcp_oidc_service_account": "weights-reader@example.iam.gserviceaccount.com",
        * "gcp_oidc_workload_id_provider": "projects/123456789/locations/global/workloadIdentityPools/baseten/providers/baseten"
        * }
        {
        * "auth_method": "AWS_ASSUME_ROLE",
        * "aws_assume_role_arn": "arn:aws:iam::123456789012:role/baseten-customer-access",
        * "aws_assume_role_region": "us-east-1"
        * }
      • Optionalauth_secret_name?: string | null

        Auth Secret Name

        Name of the workspace secret for authentication (e.g., HuggingFace token)

        hf_token
        
        aws_credentials
        
      • Optionalignore_patterns?: string[] | null

        Ignore Patterns

        File patterns to exclude (Unix-style shell patterns)

        [
        "*.bin",
        "*.h5"
        ]
      • mount_location: string

        Mount Location

        Path where weights will be mounted in the container

        /app/models/base
        
        /models/llama
        
      • source: string

        Source

        Weight source URI. Supported formats: hf://, s3://, gs://, r2://, cw://

        hf://meta-llama/Llama-3-8B@main
        
        s3://my-bucket/models/llama
        
        gs://my-bucket/models/llama
        
        r2://account_id.bucket/models/llama
        
        r2://account_id.eu.bucket/models/llama
        
        cw://my-bucket/models/llama
        
    • CreateLibraryListingRequest: {
          closed_source?: boolean;
          display_name: string;
          is_public?: boolean;
          user_defined_id: string;
      }

      CreateLibraryListingRequestV1

      Request to create a new library listing.

      • Optionalclosed_source?: boolean

        Closed Source

        Whether the listing is closed source (deployers cannot view or download the Truss, and forks copy mirrored weights instead of re-mirroring from upstream)

      • display_name: string

        Display Name

        Display name of the library listing

      • Optionalis_public?: boolean

        Is Public

        Whether the listing is publicly accessible

      • user_defined_id: string

        User Defined Id

        User-defined identifier of the library listing

    • CreateLibraryListingVersionRequest: {
          allow_truss_download?: boolean;
          closed_source?: boolean;
          display_name?: string | null;
          is_public?: boolean;
          oracle_version_id: string;
          version_tag: string;
      }

      CreateLibraryListingVersionRequestV1

      Request to create a new library listing version from an existing model version.

      • Optionalallow_truss_download?: boolean

        Allow Truss Download

        Whether users deploying this model can download the Truss

      • Optionalclosed_source?: boolean

        Closed Source

        Whether the listing is closed source (deployers cannot view or download the Truss, and forks copy mirrored weights instead of re-mirroring from upstream). Only used when creating a new listing.

      • Optionaldisplay_name?: string | null

        Display Name

        Display name of the library listing. Required when creating a new listing.

      • Optionalis_public?: boolean

        Is Public

        Whether the listing is publicly accessible. Only used when creating a new listing.

      • oracle_version_id: string

        Oracle Version Id

        Id of the source model version to publish

      • version_tag: string

        Version Tag

        Human-readable tag for this version

    • CreateLLMModelRequest: {
          additional_autoscaling_config?: { [key: string]: unknown } | null;
          autoscaling_settings?:
              | components["schemas"]["UpdateAutoscalingSettings"]
              | null;
          environment_variables?: { [key: string]: unknown };
          llm_config?: { [key: string]: unknown };
          llm_version?: string | null;
          metadata?: { [key: string]: unknown } | null;
          model_metadata?: { [key: string]: unknown } | null;
          name: string;
          region?: string | null;
          resources: { [key: string]: unknown };
          weights?: { [key: string]: unknown }[] | null;
      }

      CreateLLMModelRequestV1

      A request to create a BIS-LLM model

      • Optionaladditional_autoscaling_config?: { [key: string]: unknown } | null

        Additional Autoscaling Config

        Additional autoscaling configuration (e.g. target in-flight tokens)

        {
        * "metrics": [
        * {
        * "name": "in_flight_tokens",
        * "target": 40000
        * }
        * ]
        * }
      • Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | null

        Autoscaling settings for the model

        {
        * "autoscaling_window": 600,
        * "concurrency_target": null,
        * "max_replica": 5,
        * "max_scale_down_rate": null,
        * "min_replica": 1,
        * "scale_down_delay": 300,
        * "target_in_flight_tokens": null,
        * "target_utilization_percentage": null
        * }
      • Optionalenvironment_variables?: { [key: string]: unknown }

        Environment Variables

        Environment variables for the model

      • Optionalllm_config?: { [key: string]: unknown }

        Llm Config

        Configuration specific to the LLM model

      • Optionalllm_version?: string | null

        Llm Version

        Version of the helm chart to use.

      • Optionalmetadata?: { [key: string]: unknown } | null

        Metadata

        User-defined metadata for the deployment

        {
        * "environment": "production",
        * "git_sha": "abc123"
        * }
      • Optionalmodel_metadata?: { [key: string]: unknown } | null

        Model Metadata

        Model metadata persisted into model_config

      • name: string

        Name

        Name of the model

      • Optionalregion?: string | null

        Region

        Region in which to deploy the model

      • resources: { [key: string]: unknown }

        Resources

        Resources allocated to the model

      • Optionalweights?: { [key: string]: unknown }[] | null

        Weights

        Weight configurations for BDN model weight distribution

        [
        {
        "mount_location": "/models/base",
        "source": "hf://meta-llama/Llama-3-8B"
        }
        ]
    • CreateLLMModelVersionRequest: {
          additional_autoscaling_config?: { [key: string]: unknown } | null;
          autoscaling_settings?:
              | components["schemas"]["UpdateAutoscalingSettings"]
              | null;
          environment_variables?: { [key: string]: unknown };
          llm_config?: { [key: string]: unknown };
          llm_version?: string | null;
          metadata?: { [key: string]: unknown } | null;
          model_metadata?: { [key: string]: unknown } | null;
          region?: string | null;
          resources: { [key: string]: unknown };
          weights?: { [key: string]: unknown }[] | null;
      }

      CreateLLMModelVersionRequestV1

      A request to create a BIS-LLM model version

      • Optionaladditional_autoscaling_config?: { [key: string]: unknown } | null

        Additional Autoscaling Config

        Additional autoscaling configuration (e.g. target in-flight tokens)

        {
        * "metrics": [
        * {
        * "name": "in_flight_tokens",
        * "target": 40000
        * }
        * ]
        * }
      • Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | null

        Autoscaling settings for the model

        {
        * "autoscaling_window": 600,
        * "concurrency_target": null,
        * "max_replica": 5,
        * "max_scale_down_rate": null,
        * "min_replica": 1,
        * "scale_down_delay": 300,
        * "target_in_flight_tokens": null,
        * "target_utilization_percentage": null
        * }
      • Optionalenvironment_variables?: { [key: string]: unknown }

        Environment Variables

        Environment variables for the model

      • Optionalllm_config?: { [key: string]: unknown }

        Llm Config

        Configuration specific to the LLM model

      • Optionalllm_version?: string | null

        Llm Version

        Version of the helm chart to use.

      • Optionalmetadata?: { [key: string]: unknown } | null

        Metadata

        User-defined metadata for the deployment

        {
        * "environment": "production",
        * "git_sha": "abc123"
        * }
      • Optionalmodel_metadata?: { [key: string]: unknown } | null

        Model Metadata

        Model metadata persisted into model_config

      • Optionalregion?: string | null

        Region

        Region in which to deploy the model

      • resources: { [key: string]: unknown }

        Resources

        Resources allocated to the model

      • Optionalweights?: { [key: string]: unknown }[] | null

        Weights

        Weight configurations for BDN model weight distribution

        [
        {
        "mount_location": "/models/base",
        "source": "hf://meta-llama/Llama-3-8B"
        }
        ]
    • CreateLoopsRunRequest: {
          availability_model?: components["schemas"]["V1AvailabilityModel"];
          base_model: string;
          lora_rank?: number;
          max_seq_len?: number | null;
          name?: string | null;
          path?: string | null;
          replicas?: number;
          reuse_from_run_id?: string | null;
          reuse_from_session_id?: string | null;
          scale_down_delay_seconds?: number;
          seed?: number | null;
          session_id: string;
      }

      CreateLoopsRunRequestV1

      • Optionalavailability_model?: components["schemas"]["V1AvailabilityModel"]

        Capacity the trainer runs on. 'dedicated' is not preempted. 'spot' runs below inference and reaches idle reserved capacity, but the run is stopped if its GPUs are reclaimed and cannot be resumed.

        spot
        
      • base_model: string

        Base Model

        Base model ID (e.g. 'Qwen/Qwen3-8B').

      • Optionallora_rank?: number

        Lora Rank

        LoRA rank.

      • Optionalmax_seq_len?: number | null

        Max Seq Len

        Maximum prompt length (in tokens) the run must handle. Set this to the longest training example you plan to send. Defaults to the maximum supported by the model configuration.

      • Optionalname?: string | null

        Name

        Optional display name for the run. Defaults to the base model name when omitted.

      • Optionalpath?: string | null

        Path

        Optional bt:// URI of an existing checkpoint to load weights from on startup. Form: bt://loops:<run_id>/weights/<checkpoint_name>.

        bt://loops:k4q95w5/weights/step-100
        
      • Optionalreplicas?: number

        Replicas

        Number of data-parallel trainer replicas. Each replica is one full copy of the model's preset node group, so the trainer deployment runs (preset node_count * replicas) nodes (e.g. replicas=4 on a 4-node preset → 16 nodes, 4 DP workers). Must be a positive integer. Defaults to 1.

      • Optionalreuse_from_run_id?: string | null

        Reuse From Run Id

        Optional ID of a prior Loops run whose trainer and/or sampler should be reused for this run instead of provisioning fresh. The prior run must use the same base model and belong to the same team.

      • Optionalreuse_from_session_id?: string | null

        Reuse From Session Id

        Optional ID of a prior Loops session whose trainer and/or sampler should be reused for this run. Deprecated in favor of reuse_from_run_id.

      • Optionalscale_down_delay_seconds?: number

        Scale Down Delay Seconds

        Seconds of inactivity before the run scales to zero. Must be between 1 and 3600 (1 hour). Defaults to 900 (15 minutes).

      • Optionalseed?: number | null

        Seed

        Random seed for reproducibility.

      • session_id: string

        Session Id

        ID of the Loops session this run belongs to.

    • CreateLoopsRunResponse: { run: components["schemas"]["LoopsRun"] }

      CreateLoopsRunResponseV1

    • CreateLoopsSamplerRequest: {
          base_model?: string | null;
          max_seq_length?: number | null;
          model_path?: string | null;
          reuse_from_session_id?: string | null;
          run_id?: string | null;
          session_id: string;
      }

      CreateLoopsSamplerRequestV1

      • Optionalbase_model?: string | null

        Base Model

        Base model ID for a standalone sampler (for example, a baseline).

      • Optionalmax_seq_length?: number | null

        Max Seq Length

        Maximum prompt length (in tokens) the sampler must handle. Set this to the longest prompt you plan to send.

      • Optionalmodel_path?: string | null

        Model Path

        bt:// URI of an existing sampler checkpoint to serve. Form: bt://loops:<run_id>/sampler_weights/<checkpoint_name>.

        bt://loops:k4q95w5/sampler_weights/step-100
        
      • Optionalreuse_from_session_id?: string | null

        Reuse From Session Id

        Optional ID of a prior Loops session to reuse a trainer and/or sampler from. Deprecated.

      • Optionalrun_id?: string | null

        Run Id

        ID of an existing run to attach this sampler to. When set, the sampler is paired to the run and weight-syncs from its trainer, and base_model is inherited from the run. Omit to create a standalone sampler.

      • session_id: string

        Session Id

        ID of the Loops session this sampler belongs to.

    • CreateLoopsSamplerResponse: { sampler: components["schemas"]["LoopsSampler"] }

      CreateLoopsSamplerResponseV1

    • CreateLoopsSessionResponse: { session: components["schemas"]["LoopsSession"] }

      CreateLoopsSessionResponseV1

    • CreateModelDeploymentRequest: { source: components["schemas"]["DeploymentArchiveSource"] }

      CreateModelDeploymentRequestV1

      Body for adding a deployment to an existing model via POST /v1/models/{model_id}/deployments.

      • source: components["schemas"]["DeploymentArchiveSource"]

        Source

        Where the new deployment is created from.

    • CreateModelRequest: {
          source:
              | components["schemas"]["LibraryListingSource"]
              | components["schemas"]["ModelArchiveSource"];
      }

      CreateModelRequestV1

      Body for creating a model via POST /v1/models.

    • CreateTrainingJob: {
          compute?: components["schemas"]["CreateTrainingJobCompute"];
          enable_baseten_workdir?: boolean;
          image: components["schemas"]["CreateTrainingJobImage"];
          interactive_session?:
              | components["schemas"]["InteractiveSessionConfig"]
              | null;
          name?: string
          | null;
          priority?: number | null;
          runtime?: components["schemas"]["CreateTrainingJobRuntime"];
          truss_user_env?: components["schemas"]["TrussUserEnv"] | null;
          weights?: components["schemas"]["CreateJobWeightConfig"][];
      }

      CreateTrainingJobV1

      Configuration for a training job.

      • Optionalcompute?: components["schemas"]["CreateTrainingJobCompute"]
        {
        * "accelerator": {
        * "accelerator": "H100",
        * "count": 2
        * },
        * "availability_model": "spot",
        * "cpu_count": 1,
        * "memory": "2Gi",
        * "node_count": 1
        * }
      • Optionalenable_baseten_workdir?: boolean

        Enable Baseten Workdir

        When enabled, uses /b10/workspace as the working directory instead of the image WORKDIR.

        false
        
        true
        
      • image: components["schemas"]["CreateTrainingJobImage"]
        {
        * "base_image": "hello-world",
        * "docker_auth": null
        * }
      • Optionalinteractive_session?: components["schemas"]["InteractiveSessionConfig"] | null

        Configuration for interactive debugging sessions.

      • Optionalname?: string | null

        Name

        Name of the training job.

        gpt-oss-job
        
      • Optionalpriority?: number | null

        Priority

        Queue priority. Higher values are dequeued first. Defaults to 0.

        0
        
        10
        
        100
        
      • Optionalruntime?: components["schemas"]["CreateTrainingJobRuntime"]

        Configuration for the runtime environment of the training job.

        {
        * "artifacts": [],
        * "cache_config": null,
        * "checkpointing_config": {
        * "checkpoint_path": null,
        * "enabled": false,
        * "volume_size_gib": null
        * },
        * "enable_cache": null,
        * "environment_variables": {
        * "API_KEY": "your_api_key_here",
        * "PATH": "/usr/bin"
        * },
        * "load_checkpoint_config": null,
        * "start_commands": [
        * "python main.py"
        * ]
        * }
      • Optionaltruss_user_env?: components["schemas"]["TrussUserEnv"] | null

        Truss user environment information

      • Optionalweights?: components["schemas"]["CreateJobWeightConfig"][]

        Weights

        MDN weight sources to mount in the training container. Weights are mirrored and cached for fast startup.

        [
        {
        "allow_patterns": null,
        "auth": null,
        "auth_secret_name": null,
        "ignore_patterns": null,
        "mount_location": "/app/models/base",
        "source": "hf://meta-llama/Llama-3-8B@main"
        }
        ]
    • CreateTrainingJobAccelerator: { accelerator: string; count: number }

      CreateTrainingJobAcceleratorV1

      • accelerator: string

        Accelerator

        GPU type for the training job.

        H100
        
      • count: number

        Count

        GPUs needed for the training job.

        2
        
    • CreateTrainingJobCacheConfig: {
          enable_legacy_hf_mount?: boolean;
          enabled?: boolean;
          mount_base_path?: string;
          require_cache_affinity?: boolean;
      }

      CreateTrainingJobCacheConfig

      • Optionalenable_legacy_hf_mount?: boolean

        Enable Legacy Hf Mount

        Whether to enable the legacy Hugging Face cache.

        true
        
      • Optionalenabled?: boolean

        Enabled

        Whether to enable the read-write cache.

        true
        
      • Optionalmount_base_path?: string

        Mount Base Path

        Mount base path for the cache directory. The project cache and team cache will be mounted under this path.

        /workspace/.cache
        
        /root/.cache
        
      • Optionalrequire_cache_affinity?: boolean

        Require Cache Affinity

        Whether to require region affinity for the read-write cache. If False, the resulting job is not guaranteed to be deployed alongside the previous cache.

        true
        
        false
        
    • CreateTrainingJobCheckpointingConfig: {
          checkpoint_path?: string | null;
          enabled?: boolean;
          volume_size_gib?: number | null;
      }

      CreateTrainingJobCheckpointingConfig

      • Optionalcheckpoint_path?: string | null

        Checkpoint Path

        path where checkpoints will be saved.

        /mnt/ckpts
        
      • Optionalenabled?: boolean

        Enabled

        Whether checkpointing is enabled.

        true
        
      • Optionalvolume_size_gib?: number | null

        Volume Size Gib

        Size of the volume in gibibytes. If not provided, the default size will be used

        10
        
    • CreateTrainingJobCompute: {
          accelerator?:
              | components["schemas"]["CreateTrainingJobAccelerator"]
              | null;
          availability_model?: components["schemas"]["V1AvailabilityModel"];
          cpu_count?: number;
          memory?: string;
          node_count?: number;
      }

      CreateTrainingJobComputeV1

      Configuration to specify the compute for a training job.

      • Optionalaccelerator?: components["schemas"]["CreateTrainingJobAccelerator"] | null

        GPU specification for the training job

        {
        * "accelerator": "H100",
        * "count": 2
        * }
      • Optionalavailability_model?: components["schemas"]["V1AvailabilityModel"]

        Capacity guarantee for the job. 'dedicated' (the default) runs on on-demand capacity that is not preempted. 'spot' runs on interruptible capacity that may be preempted; the user is responsible for checkpointing their own progress.

        spot
        
      • Optionalcpu_count?: number

        Cpu Count

        Number of cpus for the training job.

        1
        
      • Optionalmemory?: string

        Memory

        Memory for the training job.

        2Gi
        
      • Optionalnode_count?: number

        Node Count

        Number of nodes for the training job.

        1
        
    • CreateTrainingJobImage: { base_image: string; docker_auth?: components["schemas"]["DockerAuth"] | null }

      CreateTrainingJobImageV1

      Configuration to create a training job image.

      • base_image: string

        Base Image

        Base image for the training job.

        hello-world
        
      • Optionaldocker_auth?: components["schemas"]["DockerAuth"] | null

        Docker authentication credentials

    • CreateTrainingJobRequest: { training_job: components["schemas"]["CreateTrainingJob"] }

      CreateTrainingJobRequestV1

      A request to create a training job.

      • training_job: components["schemas"]["CreateTrainingJob"]

        The training job to create.

    • CreateTrainingJobResponse: { training_job: components["schemas"]["TrainingJob"] }

      CreateTrainingJobResponseV1

      A response to creating a training job.

    • CreateTrainingJobRuntime: {
          artifacts?: components["schemas"]["CreateTrainingJobS3Artifact"][];
          cache_config?: components["schemas"]["CreateTrainingJobCacheConfig"] | null;
          checkpointing_config?: components["schemas"]["CreateTrainingJobCheckpointingConfig"];
          enable_cache?: boolean | null;
          environment_variables?: { [key: string]: string | { name: string } };
          load_checkpoint_config?:
              | components["schemas"]["LoadCheckpointConfig"]
              | null;
          start_commands?: string[];
      }

      CreateTrainingJobRuntimeV1

      Configuration to specify the runtime environment for a training job.

      • Optionalartifacts?: components["schemas"]["CreateTrainingJobS3Artifact"][]

        Artifacts

        Runtime artifacts for the training job.

      • Optionalcache_config?: components["schemas"]["CreateTrainingJobCacheConfig"] | null

        Configuration for the read-write cache.

        {
        * "enable_legacy_hf_mount": true,
        * "enabled": true,
        * "mount_base_path": "/root/.cache",
        * "require_cache_affinity": true
        * }
      • Optionalcheckpointing_config?: components["schemas"]["CreateTrainingJobCheckpointingConfig"]

        Configuration for checkpointing.

        {
        * "checkpoint_path": "/mnt/ckpts",
        * "enabled": true,
        * "volume_size_gib": null
        * }
      • Optionalenable_cache?: boolean | null

        Enable Cache

        Deprecated. Use cache_config instead.

        true
        
      • Optionalenvironment_variables?: { [key: string]: string | { name: string } }

        Environment Variables

        Environment variables to set in the runtime.

        {
        * "API_KEY": "your_api_key_here",
        * "PATH": "/usr/bin"
        * }
      • Optionalload_checkpoint_config?: components["schemas"]["LoadCheckpointConfig"] | null

        Configuration for loading checkpoints

      • Optionalstart_commands?: string[]

        Start Commands

        Commands to execute when starting the runtime.

        [
        "python main.py"
        ]
    • CreateTrainingJobS3Artifact: { s3_bucket: string; s3_key: string }

      CreateTrainingJobS3Artifact

      • s3_bucket: string

        S3 Bucket

        S3 bucket for the uploaded runtime artifact.

        my-s3-bucket
        
      • s3_key: string

        S3 Key

        S3 key for the uploaded runtime artifact.

        my-s3-key
        
    • CreateVolumeTokenRequest: {
          correlation_id?: string | null;
          namespaces: string[];
          scopes: components["schemas"]["VolumeTokenScope"][];
          volumes: string[];
      }

      CreateVolumeTokenRequestV1

      • Optionalcorrelation_id?: string | null

        Correlation Id

        Optional client-chosen identifier, at most 128 printable ASCII characters. Echoed into server logs to link the issued token to a client operation.

      • namespaces: string[]

        Namespaces

        Volume namespaces the token is limited to, lowercase ASCII, at least one. Pass only the namespaces the operation needs.

      • scopes: components["schemas"]["VolumeTokenScope"][]

        Scopes

        Capabilities the token grants, at least one. Requesting PUSH or TAG requires organization-level model management permission.

      • volumes: string[]

        Volumes

        Volume names the token is limited to, lowercase ASCII, exact names only, at least one. The limit applies to every requested scope in every requested namespace.

    • CreateVolumeTokenResponse: {
          bdn_endpoint: string | null;
          expires_at: string;
          namespaces: string[];
          scopes: components["schemas"]["VolumeTokenScope"][];
          token: string;
          volumes: string[];
      }

      CreateVolumeTokenResponseV1

      • bdn_endpoint: string | null

        Bdn Endpoint

        Base URL of the volume API this token authenticates against. Null when the environment does not expose a public volume API yet.

      • expires_at: string

        Expires At Format: date-time

        Token expiry in ISO 8601 format. Tokens cannot be renewed; exchange again for a fresh token.

      • namespaces: string[]

        Namespaces

        Effective namespaces granted, in canonical lowercase form.

      • scopes: components["schemas"]["VolumeTokenScope"][]

        Scopes

        Effective capabilities granted.

      • token: string

        Token

        Volume access token. Pass as a bearer token to the volume APIs.

      • volumes: string[]

        Volumes

        Effective volume names granted, in canonical lowercase form.

    • DailyDedicatedUsage: {
          compute_cost: number | string;
          date: string;
          inference_requests: number;
          minutes: number;
          subtotal: number | string;
          surcharge_cost: number | string;
      }

      DailyDedicatedUsageV1

      • compute_cost: number | string

        Compute Cost

        Compute cost incurred on this date in dollars

      • date: string

        Date Format: date

        Date of the usage

      • inference_requests: number

        Inference Requests

        Number of inference requests on this date

      • minutes: number

        Minutes

        Minutes used on this date

      • subtotal: number | string

        Subtotal

        Subtotal cost incurred on this date in dollars

      • surcharge_cost: number | string

        Surcharge Cost

        Model distribution surcharge incurred on this date in dollars

    • DailyModelApiUsage: {
          cached_input_tokens: number;
          date: string;
          input_tokens: number;
          output_tokens: number;
          subtotal: number | string;
      }

      DailyModelApiUsageV1

      • cached_input_tokens: number

        Cached Input Tokens

        Number of cached input tokens on this date

      • date: string

        Date Format: date

        Date of the usage

      • input_tokens: number

        Input Tokens

        Number of input tokens on this date

      • output_tokens: number

        Output Tokens

        Number of output tokens on this date

      • subtotal: number | string

        Subtotal

        Subtotal cost incurred on this date in dollars

    • DailyTrainingUsage: { date: string; minutes: number; subtotal: number | string }

      DailyTrainingUsageV1

      • date: string

        Date Format: date

        Date of the usage

      • minutes: number

        Minutes

        Minutes used on this date

      • subtotal: number | string

        Subtotal

        Subtotal cost incurred on this date in dollars

    • DeactivateLoopsDeploymentResponse: { base_model: string; id: string; user: components["schemas"]["User"] }

      DeactivateLoopsDeploymentResponseV1

      Response for POST /v1/loops/deployments/<deployment_id>/deactivate.

      • base_model: string

        Base Model

        The base model whose Loops deployment was deactivated.

      • id: string

        Id

        The deactivated Loops deployment ID.

      • user: components["schemas"]["User"]

        The user who owned the Loops deployment.

    • DeactivateLoopsRunResponse: { base_model: string; id: string; user: components["schemas"]["User"] }

      DeactivateLoopsRunResponseV1

      Response for POST /v1/loops/runs/<run_id>/deactivate.

      • base_model: string

        Base Model

        The base model whose Loops run was deactivated.

      • id: string

        Id

        The deactivated Loops run ID.

      • user: components["schemas"]["User"]

        The user who owns the Loops run.

    • DeactivateResponse: { no_op: boolean; success: boolean }

      DeactivateResponseV1

      The response to a request to deactivate a deployment.

      • no_op: boolean

        No Op

        Whether the request did nothing because the deployment was already inactive

        false
        
      • success: boolean

        Success

        Whether the deployment was successfully deactivated

        true
        
    • DedicatedItem: {
          billable_resource: components["schemas"]["BillableResource"];
          compute_cost: number | string;
          daily?: components["schemas"]["DailyDedicatedUsage"][];
          inference_requests: number;
          minutes: number;
          subtotal: number | string;
          surcharge_cost: number | string;
      }

      DedicatedItemV1

      • billable_resource: components["schemas"]["BillableResource"]

        The model deployment resource

      • compute_cost: number | string

        Compute Cost

        Compute cost in dollars for this billable resource

      • Optionaldaily?: components["schemas"]["DailyDedicatedUsage"][]

        Daily

        Daily usage breakdown

      • inference_requests: number

        Inference Requests

        Total inference requests for this billable resource

      • minutes: number

        Minutes

        Total minutes used for this billable resource

      • subtotal: number | string

        Subtotal

        Subtotal cost in dollars for this billable resource

      • surcharge_cost: number | string

        Surcharge Cost

        Model distribution surcharge in dollars for this billable resource

    • DedicatedUsage: {
          breakdown?: components["schemas"]["DedicatedItem"][];
          credits_used: number | string;
          minutes: number;
          subtotal: number | string;
          total: number | string;
      }

      DedicatedUsageV1

      • Optionalbreakdown?: components["schemas"]["DedicatedItem"][]

        Breakdown

        Per-deployment usage breakdown

      • credits_used: number | string

        Credits Used

        Credits applied in dollars

      • minutes: number

        Minutes

        Total minutes used

      • subtotal: number | string

        Subtotal

        Subtotal cost in dollars after applying credits used

      • total: number | string

        Total

        Total cost in dollars

    • DeleteVolumeRequest: { expected_sequence?: number | null }

      DeleteVolumeRequestV1

      • Optionalexpected_sequence?: number | null

        Expected Sequence

        Revision the volume is expected to be at. When set, the delete fails with a conflict if the volume has changed since, so it cannot act on a volume someone else has pushed to. Take the value from a volume's sequence, or from volume_sequence.

    • DeleteVolumeResponse: {
          name: string;
          namespace: string;
          versions_deleted: number;
          volume_sequence: number;
      }

      DeleteVolumeResponseV1

      • name: string

        Name

        Name of the volume, in lowercase.

      • namespace: string

        Namespace

        Namespace the volume belongs to, in lowercase.

      • versions_deleted: number

        Versions Deleted

        Number of versions this request deleted. Zero when the volume had no live versions left, which is not an error.

      • volume_sequence: number

        Volume Sequence

        Revision of the volume after the delete.

    • DeleteVolumeVersionRequest: { expected_sequence?: number | null }

      DeleteVolumeVersionRequestV1

      • Optionalexpected_sequence?: number | null

        Expected Sequence

        Revision the volume is expected to be at. When set, the delete fails with a conflict if the volume has changed since, so a read followed by a delete cannot act on a version a tag has since been moved off. Take the value from volume_sequence.

    • DeleteVolumeVersionResponse: {
          delete_after: string;
          digest: string;
          lifecycle: string;
          namespace: string;
          version_ref: string;
          volume: string;
          volume_sequence: number;
      }

      DeleteVolumeVersionResponseV1

      • delete_after: string

        Delete After Format: date-time

        When the version stops being restorable, in ISO 8601 format. Until then it can be returned to service.

      • digest: string

        Digest

        Content digest of the deleted version, as b3:<hex>.

      • lifecycle: string

        Lifecycle

        Lifecycle state of the version after the delete.

      • namespace: string

        Namespace

        Namespace the volume belongs to, in lowercase.

      • version_ref: string

        Version Ref

        Full address of the deleted version, as bdn:<namespace>/<volume>@<digest>.

      • volume: string

        Volume

        Name of the volume, in lowercase.

      • volume_sequence: number

        Volume Sequence

        Revision of the volume after the delete.

    • Deployment: {
          active_replica_count: number;
          autoscaling_settings: components["schemas"]["AutoscalingSettings"] | null;
          created_at: string;
          environment: string | null;
          id: string;
          instance_type_name: string | null;
          is_development: boolean;
          is_production: boolean;
          labels: { [key: string]: unknown } | null;
          model_id: string;
          name: string;
          region: components["schemas"]["Region"] | null;
          request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"];
          status: components["schemas"]["DeploymentStatus"];
      }

      DeploymentV1

      A deployment of a model.

      • active_replica_count: number

        Active Replica Count

        Number of active replicas

      • autoscaling_settings: components["schemas"]["AutoscalingSettings"] | null

        Autoscaling settings for the deployment. If null, the model has not finished deploying

      • created_at: string

        Created At Format: date-time

        Time the deployment was created in ISO 8601 format

      • environment: string | null

        Environment

        The environment associated with the deployment

      • id: string

        Id

        Unique identifier of the deployment

      • instance_type_name: string | null

        Instance Type Name

        Name of the instance type the model deployment is running on

      • is_development: boolean

        Is Development

        Whether the deployment is the development deployment of the model

      • is_production: boolean

        Is Production

        Whether the deployment is the production deployment of the model

      • labels: { [key: string]: unknown } | null

        Labels

        User-provided key-value labels for the deployment

        null
        
      • model_id: string

        Model Id

        Unique identifier of the model

      • name: string

        Name

        Name of the deployment

      • region: components["schemas"]["Region"] | null

        The selected region for the deployment, if any

        null
        
      • request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"]

        Effective request backpressure settings for the deployment.

      • status: components["schemas"]["DeploymentStatus"]

        Status of the deployment

    • DeploymentArchivePayload: {
          config: { [key: string]: unknown };
          create_environment_if_missing?: boolean;
          deploy_timeout_minutes?: number | null;
          deployment_name?: string | null;
          environment_name?: string | null;
          is_development?: boolean;
          labels?: { [key: string]: unknown } | null;
          preserve_env_instance_type?: boolean;
          raw_config?: string | null;
          region?: string | null;
          user_env?: { [key: string]: unknown } | null;
      }

      DeploymentArchivePayloadV1

      Deployment-level fields for a model-archive push.

      Shared by every endpoint that creates a deployment from an uploaded archive:
      `POST /v1/prepare_model_upload`, the `model_archive` source on `POST
      /v1/models`, and `POST /v1/models/{model_id}/deployments`.
      
      • config: { [key: string]: unknown }

        Config

        Parsed model config as a JSON object.

      • Optionalcreate_environment_if_missing?: boolean

        Create Environment If Missing

        Create the environment named by environment_name if it does not exist yet. If false, a push to an environment that does not exist is rejected. Only meaningful when environment_name is set to something other than production, which always exists. This field currently defaults to true, but that default will change to false in a future release. Set it explicitly to avoid a behavior change.

      • Optionaldeploy_timeout_minutes?: number | null

        Deploy Timeout Minutes

        Deploy timeout in minutes; allowed range 10 to 1440. Server default applies if unset.

      • Optionaldeployment_name?: string | null

        Deployment Name

        Optional human-readable name for the deployment.

      • Optionalenvironment_name?: string | null

        Environment Name

        Stable environment to push to (e.g. production). If unset, the deployment is created without environment selection. Caller must have push permission for the named environment.

      • Optionalis_development?: boolean

        Is Development

        If true, push as a development deployment: the model's single mutable dev slot, created if absent and overwritten in place otherwise. The following fields must be left at their defaults: environment_name, preserve_env_instance_type, deployment_name.

      • Optionallabels?: { [key: string]: unknown } | null

        Labels

        User-provided key-value labels for the deployment.

      • Optionalpreserve_env_instance_type?: boolean

        Preserve Env Instance Type

        Retain the target environment's current instance type rather than the one in config. Only meaningful when environment_name is set and that environment already exists.

      • Optionalraw_config?: string | null

        Raw Config

        Original config.yaml text, persisted as-is on the deployment. Best-effort: invalid raw configs are logged and dropped without failing the request.

      • Optionalregion?: string | null

        Region

        Region in which to deploy the model

      • Optionaluser_env?: { [key: string]: unknown } | null

        User Env

        Client environment metadata (e.g. client version, Python version). Validated server-side.

    • DeploymentArchiveSource: {
          deployment: components["schemas"]["DeploymentArchivePayload"];
          kind: "model_archive";
          s3_key?: string | null;
      }

      DeploymentArchiveSourceV1

      Add a deployment from an archive previously uploaded via the credentials issued by POST /v1/prepare_model_upload.

      • deployment: components["schemas"]["DeploymentArchivePayload"]

        Deployment-level configuration.

      • kind: "model_archive"

        discriminator enum property added by openapi-typescript

      • Optionals3_key?: string | null

        S3 Key

        S3 key of the uploaded archive, from the credentials returned by POST /v1/prepare_model_upload. Omit for model formats that are not built from an archive (for example, BIS-LLM), where prepare issues no upload target.

    • DeploymentConfigOutputFormat: "raw" | "parsed" | "both"

      DeploymentConfigOutputFormat

    • DeploymentConfigResponse: { config: { [key: string]: unknown } | null; raw_config: string | null }

      DeploymentConfigResponseV1

      The config of a deployment. Fields are populated per output_format.

      • config: { [key: string]: unknown } | null

        Config

        The parsed config of the deployment.

        null
        
      • raw_config: string | null

        Raw Config

        The original config.yaml text — preserves comments, ordering, formatting.

        null
        
    • DeploymentPatchAction: "ADD" | "UPDATE" | "REMOVE"

      DeploymentPatchActionV1

      How a patch op changes its target.

    • DeploymentPatchOpConfig: { config: { [key: string]: unknown }; path?: string; type: "config" }

      DeploymentPatchOpConfigV1

      Replace the config when config.yaml changes.

      Config has no action: it is always a full replacement of the parsed config.
      Derived changes (environment variables, external data, requirements) are
      emitted as their own ops alongside this one.
      
      • config: { [key: string]: unknown }

        Config

        The full parsed config as a JSON object.

      • Optionalpath?: string

        Path

        Config file path within the source.

      • type: "config"

        discriminator enum property added by openapi-typescript

    • DeploymentPatchOpEnvVar: {
          action: components["schemas"]["DeploymentPatchAction"];
          name: string;
          type: "environment_variable";
          value?: string | null;
      }

      DeploymentPatchOpEnvVarV1

      Add, update, or remove a single environment variable.

      • action: components["schemas"]["DeploymentPatchAction"]

        How this op changes the variable.

      • name: string

        Name

        The environment variable name.

      • type: "environment_variable"

        discriminator enum property added by openapi-typescript

      • Optionalvalue?: string | null

        Value

        The environment variable value. Required for add and update.

    • DeploymentPatchOpExternalData: {
          action: components["schemas"]["DeploymentPatchAction"];
          item: { [key: string]: string };
          type: "external_data";
      }

      DeploymentPatchOpExternalDataV1

      Add, update, or remove a single external data item.

      External data is referenced by config, not stored in the source. The backend
      only adds or removes it, where adding re-downloads (overwriting any existing
      file), so `update` is accepted and treated identically to `add`.
      
      • action: components["schemas"]["DeploymentPatchAction"]

        How this op changes the item. UPDATE is treated identically to ADD.

      • item: { [key: string]: string }

        Item

        The single external data item descriptor.

      • type: "external_data"

        discriminator enum property added by openapi-typescript

    • DeploymentPatchOpModelCode: {
          action: components["schemas"]["DeploymentPatchAction"];
          content?: string | null;
          content_bytes?: string | null;
          hot_reload?: boolean;
          path: string;
          type: "model_code";
      }

      DeploymentPatchOpModelCodeV1

      Add, update, or remove a file under the model code directory.

      • action: components["schemas"]["DeploymentPatchAction"]

        How this op changes the file.

      • Optionalcontent?: string | null

        Content

        UTF-8 file content. Null for removals and binary files.

      • Optionalcontent_bytes?: string | null

        Content Bytes

        Base64-encoded content for binary files.

      • Optionalhot_reload?: boolean

        Hot Reload

        Whether the running server can pick up this change without a restart.

      • path: string

        Path

        File path relative to the model code directory.

      • type: "model_code"

        discriminator enum property added by openapi-typescript

    • DeploymentPatchOpPackage: {
          action: components["schemas"]["DeploymentPatchAction"];
          content?: string | null;
          content_bytes?: string | null;
          path: string;
          type: "package";
      }

      DeploymentPatchOpPackageV1

      Add, update, or remove a file under the bundled packages directory.

      • action: components["schemas"]["DeploymentPatchAction"]

        How this op changes the file.

      • Optionalcontent?: string | null

        Content

        UTF-8 file content. Null for removals and binary files.

      • Optionalcontent_bytes?: string | null

        Content Bytes

        Base64-encoded content for binary files.

      • path: string

        Path

        File path relative to the bundled packages directory.

      • type: "package"

        discriminator enum property added by openapi-typescript

    • DeploymentPatchOpPythonRequirement: {
          action: components["schemas"]["DeploymentPatchAction"];
          requirement: string;
          type: "python_requirement";
      }

      DeploymentPatchOpPythonRequirementV1

      Add, update, or remove a single Python requirement.

      • action: components["schemas"]["DeploymentPatchAction"]

        How this op changes the requirement.

      • requirement: string

        Requirement

        The requirement to apply. For removals this is the package name; otherwise the full requirements.txt-style line.

      • type: "python_requirement"

        discriminator enum property added by openapi-typescript

    • DeploymentPatchPoint: {
          config: string;
          content_hashes: { [key: string]: string | null };
          requirements?: string[];
      }

      DeploymentPatchPointV1

      A patch point: the source state the next patch is computed against.

      The content hash that identifies a point is derived from this state (see
      `DeploymentPatchPointWithHashV1.hash`), so a request only sends the state and
      the server stamps the hash. A previous point's hash plus the current local
      source is enough to compute the next patch, so the watch client reads the
      point it is patching off of.
      
      • config: string

        Config

        The verbatim config.yaml text for this source state.

      • content_hashes: { [key: string]: string | null }

        Content Hashes

        Map of every non-ignored source path, relative and forward-slash, to its content hash: files map to the hex blake3 digest of their bytes, directories map to null. This is the full signature of the source tree and what the content hash is derived from.

      • Optionalrequirements?: string[]

        Requirements

        Requirements resolved from the config's requirements file, when it points at one. Empty when requirements are declared inline in the config.

    • DeploymentPatchPointWithHash: {
          config: string;
          content_hashes: { [key: string]: string | null };
          hash: string;
          requirements?: string[];
      }

      DeploymentPatchPointWithHashV1

      A patch point plus its server-assigned content hash, returned in responses.

      Requests omit the hash (the server derives it from the source state); responses
      include it so the watch client can echo it back as the next patch's
      `prev_patch_hash` without having to recompute the fold itself.
      
      • config: string

        Config

        The verbatim config.yaml text for this source state.

      • content_hashes: { [key: string]: string | null }

        Content Hashes

        Map of every non-ignored source path, relative and forward-slash, to its content hash: files map to the hex blake3 digest of their bytes, directories map to null. This is the full signature of the source tree and what the content hash is derived from.

      • hash: string

        Hash

        Content hash identifying this exact source state, and the link patches build on. It is derived deterministically from content_hashes, so a request need not send it - the server derives it. It is derived by sorting the content_hashes keys as paths, splitting each key on '/' into its path components and ordering the keys by comparing those component lists element by element, each component compared by Unicode code point (equivalently UTF-8 byte order). Treating '/' as a path separator this way, rather than as the ordinary character U+002F, means a key that is an ancestor path sorts before a sibling whose name extends the first differing component (so e.g. 'a/b' sorts before 'a.b'). A blake3 hasher is then built, and for each key in that order updated with the blake3 digest (32 raw bytes) of the key encoded as UTF-8, then, when the entry is a file (non-null value), with that file's digest as 32 raw bytes. The stream uses raw digest bytes, but the values in content_hashes are those digests hex-encoded (64 hex chars), so decode each value from hex first. Directory entries (null value) contribute only their key digest. The result is the hasher's own hex digest.

      • Optionalrequirements?: string[]

        Requirements

        Requirements resolved from the config's requirements file, when it points at one. Empty when requirements are declared inline in the config.

    • Deployments: { deployments: components["schemas"]["Deployment"][] }

      DeploymentsV1

      A list of deployments of a model.

      • deployments: components["schemas"]["Deployment"][]

        Deployments

        A list of deployments of a model

    • DeploymentStatus:
          | "BUILDING"
          | "DEPLOYING"
          | "DEPLOY_FAILED"
          | "LOADING_MODEL"
          | "ACTIVE"
          | "UNHEALTHY"
          | "BUILD_FAILED"
          | "BUILD_STOPPED"
          | "DEACTIVATING"
          | "INACTIVE"
          | "FAILED"
          | "UPDATING"
          | "SCALED_TO_ZERO"
          | "WAKING_UP"

      DeploymentStatusV1

      The status of a deployment.

    • DeploymentTombstone: { deleted: boolean; id: string; model_id: string }

      DeploymentTombstoneV1

      A model deployment tombstone.

      • deleted: boolean

        Deleted

        Whether the deployment was deleted

      • id: string

        Id

        Unique identifier of the deployment

      • model_id: string

        Model Id

        Unique identifier of the model

    • DockerAuth: {
          auth_method: components["schemas"]["DockerAuthType"];
          aws_assume_role_docker_auth?:
              | components["schemas"]["AwsAssumeRoleDockerAuth"]
              | null;
          aws_iam_docker_auth?: components["schemas"]["AwsIamDockerAuth"]
          | null;
          aws_oidc_docker_auth?: components["schemas"]["AwsOidcDockerAuth"] | null;
          gcp_oidc_docker_auth?: components["schemas"]["GcpOidcDockerAuth"] | null;
          gcp_service_account_json_docker_auth?:
              | components["schemas"]["GcpServiceAccountJsonDockerAuth"]
              | null;
          registry: string;
          registry_secret_docker_auth?: | components["schemas"]["RegistrySecretDockerAuth"]
          | null;
      }

      DockerAuthV1

      Docker authentication credentials.

      • auth_method: components["schemas"]["DockerAuthType"]

        Method to authenticate with the registry

        GCP_SERVICE_ACCOUNT_JSON
        
        AWS_IAM
        
        AWS_OIDC
        
        GCP_OIDC
        
        REGISTRY_SECRET
        
        AWS_ASSUME_ROLE
        
      • Optionalaws_assume_role_docker_auth?: components["schemas"]["AwsAssumeRoleDockerAuth"] | null

        Required when auth_method is AWS_ASSUME_ROLE. Baseten assumes the given IAM role with its own AWS principal and your organization's external ID, with no OIDC provider registration in your account.

      • Optionalaws_iam_docker_auth?: components["schemas"]["AwsIamDockerAuth"] | null

        AWS details for the registry

      • Optionalaws_oidc_docker_auth?: components["schemas"]["AwsOidcDockerAuth"] | null

        AWS OIDC details for the registry

      • Optionalgcp_oidc_docker_auth?: components["schemas"]["GcpOidcDockerAuth"] | null

        GCP OIDC details for the registry

      • Optionalgcp_service_account_json_docker_auth?: components["schemas"]["GcpServiceAccountJsonDockerAuth"] | null

        GCP service account details for the registry

      • registry: string

        Registry

        Registry to authenticate with

      • Optionalregistry_secret_docker_auth?: components["schemas"]["RegistrySecretDockerAuth"] | null

        Required when auth_method is REGISTRY_SECRET. Supports any Docker registry (Docker Hub, GHCR, NGC, etc.) via username:password credentials stored as a Baseten secret.

    • DockerAuthType:
          | "GCP_SERVICE_ACCOUNT_JSON"
          | "AWS_IAM"
          | "AWS_OIDC"
          | "GCP_OIDC"
          | "REGISTRY_SECRET"
          | "AWS_ASSUME_ROLE"

      DockerAuthType

    • DownloadDeploymentResponse: { download_url: string }

      DownloadDeploymentResponseV1

      The response to a request to download a deployment's truss.

      • download_url: string

        Download Url

        Presigned URL to download the truss tar file

    • DownloadTrainingJobResponse: { artifact_presigned_urls: string[] }

      DownloadTrainingJobResponseV1

      A response with presigned URLs for a training job's artifacts.

      • artifact_presigned_urls: string[]

        Artifact Presigned Urls

        Presigned URLs for the job's uploaded artifacts.

    • EffectiveModelConfig: {
          rate_limits?: components["schemas"]["EffectiveRateLimit"][];
          slug: string;
          usage_limits?: components["schemas"]["EffectiveUsageLimit"][];
      }

      EffectiveModelConfigV1

      • Optionalrate_limits?: components["schemas"]["EffectiveRateLimit"][]

        Rate Limits

      • slug: string

        Slug

        Shared endpoint slug.

      • Optionalusage_limits?: components["schemas"]["EffectiveUsageLimit"][]

        Usage Limits

    • EffectiveRateLimit: {
          source_group: string;
          threshold: number;
          type: components["schemas"]["LimitType"];
          unit: components["schemas"]["RateLimitUnit"];
      }

      EffectiveRateLimitV1

      • source_group: string

        Source Group

        ID of the group in the hierarchy this limit is anchored to.

        abc123
        
      • threshold: number

        Threshold

        The threshold for the rate limit

        1000
        
        50000
        
      • type: components["schemas"]["LimitType"]

        The type of the rate limit

        TOKEN
        
        REQUEST
        
      • unit: components["schemas"]["RateLimitUnit"]

        The unit of the rate limit

        SECOND
        
        MINUTE
        
    • EffectiveUsageLimit: {
          source_group: string;
          threshold: number;
          type: components["schemas"]["LimitType"];
          unit: components["schemas"]["UsageLimitUnit"];
      }

      EffectiveUsageLimitV1

      • source_group: string

        Source Group

        ID of the group in the hierarchy this limit is anchored to.

        abc123
        
      • threshold: number

        Threshold

        The threshold for the usage limit

        10000000
        
      • type: components["schemas"]["LimitType"]

        The type of the usage limit

        REQUEST
        
        TOKEN
        
      • unit: components["schemas"]["UsageLimitUnit"]

        The unit of the usage limit

        DAY
        
    • EmbeddingBenchmarkMetrics: {
          e2e_latency_ms_p50?: number | null;
          e2e_latency_ms_p99?: number | null;
          input_tokens_per_sec?: number | null;
          requests_per_sec?: number | null;
      }

      EmbeddingBenchmarkMetricsV1

      • Optionale2e_latency_ms_p50?: number | null

        E2E Latency Ms P50

      • Optionale2e_latency_ms_p99?: number | null

        E2E Latency Ms P99

      • Optionalinput_tokens_per_sec?: number | null

        Input Tokens Per Sec

      • Optionalrequests_per_sec?: number | null

        Requests Per Sec

    • Endpoint: {
          created_at: string;
          id: string;
          region: components["schemas"]["SharedEndpointRegion"];
          slug: string;
          targets: components["schemas"]["EndpointTarget"][];
          updated_at: string;
      }

      EndpointV1

      A Gateway endpoint: a slug and its priority-ordered targets (index 0 tried first).

      • created_at: string

        Created At Format: date-time

        Creation time, ISO 8601.

      • id: string

        Id

        Stable identifier for the endpoint.

      • region: components["schemas"]["SharedEndpointRegion"]

        Region this endpoint's routing serves.

      • slug: string

        Slug

        Globally-unique routing slug.

        baseten/mymodel-4
        
      • targets: components["schemas"]["EndpointTarget"][]

        Targets

        The endpoint's upstream targets. Exactly one target is supported at this time.

      • updated_at: string

        Updated At Format: date-time

        Last update time, ISO 8601.

    • EndpointsResponse: {
          items: components["schemas"]["Endpoint"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      EndpointsResponseV1

    • EndpointTarget: {
          base_url: string | null;
          environment_name: string | null;
          model_id: string | null;
          provider: components["schemas"]["GatewayProvider"];
          secret_id: string | null;
          target_model: string | null;
          vertex_config: components["schemas"]["VertexTargetConfig"] | null;
      }

      EndpointTargetV1

      One configured upstream target of an endpoint.

      • base_url: string | null

        Base Url

        Custom OpenAI-compatible base URL, if any.

        null
        
      • environment_name: string | null

        Environment Name

        Baseten model environment, if non-production.

        null
        
      • model_id: string | null

        Model Id

        Baseten model, if any.

        null
        
      • provider: components["schemas"]["GatewayProvider"]

        Upstream provider.

      • secret_id: string | null

        Secret Id

        Referenced secret, if any.

        null
        
      • target_model: string | null

        Target Model

        Upstream model name, if any.

        null
        
      • vertex_config: components["schemas"]["VertexTargetConfig"] | null

        Google Vertex configuration, if any.

        null
        
    • EndpointTargetRequest: {
          base_url?: string | null;
          environment_name?: string | null;
          model_id?: string | null;
          provider: components["schemas"]["GatewayProvider"];
          secret_id?: string | null;
          target_model?: string | null;
          vertex_config?: components["schemas"]["VertexTargetConfig"] | null;
      }

      EndpointTargetRequestV1

      One desired upstream target. The customer picks a provider; Baseten owns the upstream host and protocol adapter.

      • Optionalbase_url?: string | null

        Base Url

        HTTPS base URL of the upstream OpenAI-compatible server. Must not include a port. Required for and only valid with OPENAI_COMPATIBLE.

        https://my-vllm.example.com
        
      • Optionalenvironment_name?: string | null

        Environment Name

        Baseten model environment to route to. Only valid with BASETEN. Omit or pass production to target production.

        staging
        
      • Optionalmodel_id?: string | null

        Model Id

        Baseten model to route to. Required for and only valid with BASETEN.

        3kZ9xqd
        
      • provider: components["schemas"]["GatewayProvider"]

        Upstream provider for this target.

        ANTHROPIC
        
        OPENAI
        
        OPENAI_COMPATIBLE
        
        BASETEN
        
      • Optionalsecret_id?: string | null

        Secret Id

        Secret holding the provider credential. Required for external providers.

        3kZ9xqd
        
      • Optionaltarget_model?: string | null

        Target Model

        Model name to send upstream. Required for external providers and optional for BASETEN targets.

        gpt-4o
        
      • Optionalvertex_config?: components["schemas"]["VertexTargetConfig"] | null

        Google Vertex configuration. Required for and only valid with VERTEX.

    • EndpointTombstone: { id: string; slug: string }

      EndpointTombstoneV1

      • id: string

        Id

        Identifier of the deleted endpoint.

      • slug: string

        Slug

        Slug of the deleted endpoint.

    • Environment: {
          autoscaling_schedules:
              | components["schemas"]["EnvironmentAutoscalingSchedules"]
              | null;
          autoscaling_settings: components["schemas"]["AutoscalingSettings"];
          candidate_deployment: components["schemas"]["Deployment"]
          | null;
          created_at: string;
          current_deployment: components["schemas"]["Deployment"] | null;
          in_progress_promotion: components["schemas"]["InProgressPromotion"] | null;
          instance_type: components["schemas"]["InstanceType"];
          model_id: string;
          name: string;
          promotion_settings: components["schemas"]["PromotionSettings"];
          request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"];
      }

      EnvironmentV1

      Environment for oracles.

      • autoscaling_schedules: components["schemas"]["EnvironmentAutoscalingSchedules"] | null

        Autoscaling schedules and their evaluated state

        null
        
      • autoscaling_settings: components["schemas"]["AutoscalingSettings"]

        Autoscaling settings for the environment

      • candidate_deployment: components["schemas"]["Deployment"] | null

        Candidate deployment being promoted to the environment, if a promotion is in progress

        null
        
      • created_at: string

        Created At Format: date-time

        Time the environment was created in ISO 8601 format

      • current_deployment: components["schemas"]["Deployment"] | null

        Current deployment of the environment

      • in_progress_promotion: components["schemas"]["InProgressPromotion"] | null

        Details of the in-progress promotion, if any

        null
        
      • instance_type: components["schemas"]["InstanceType"]

        Instance type for the environment

      • model_id: string

        Model Id

        Unique identifier of the model

      • name: string

        Name

        Name of the environment

      • promotion_settings: components["schemas"]["PromotionSettings"]

        Promotion settings for the environment

      • request_backpressure_settings: components["schemas"]["RequestBackpressureSettings"]

        Request backpressure settings for the environment.

    • EnvironmentAutoscalingSchedules: {
          applied_state: components["schemas"]["AutoscalingScheduleState"] | null;
          schedules: (
              | components["schemas"]["AutoscalingSchedule"]
              | components["schemas"]["OneTimeAutoscalingSchedule"]
          )[];
          timezone: string
          | null;
      }

      EnvironmentAutoscalingSchedulesV1

      • applied_state: components["schemas"]["AutoscalingScheduleState"] | null

        Autoscaling state on the current serving deployment, or null when no deployment exists

      • schedules: (
            | components["schemas"]["AutoscalingSchedule"]
            | components["schemas"]["OneTimeAutoscalingSchedule"]
        )[]

        Schedules

        Autoscaling schedules ordered by creation time and stable identifier

      • timezone: string | null

        Timezone

        IANA timezone shared by all schedules. Omitted when no schedules exist.

        null
        
    • EnvironmentGroup: {
          manage_access: components["schemas"]["EnvironmentGroupManageAccess"];
          name: string;
          team_id: string;
          team_name: string;
      }

      EnvironmentGroupV1

      A team-scoped grouping of same-named environments (e.g. "production", "staging").

      Restricting an environment group limits who can manage the environment of that name
      across every model and chain in the team.
      
      • manage_access: components["schemas"]["EnvironmentGroupManageAccess"]

        Settings controlling who can manage this environment group.

      • name: string

        Name

        Name of the environment group, matching the environment name it governs.

        staging
        
      • team_id: string

        Team Id

        Unique identifier of the team the environment group belongs to.

      • team_name: string

        Team Name

        Name of the team the environment group belongs to.

    • EnvironmentGroupManageAccess: {
          is_restricted: boolean;
          users?: components["schemas"]["EnvironmentGroupUser"][];
      }

      EnvironmentGroupManageAccessV1

      Who is allowed to manage an environment group.

      • is_restricted: boolean

        Is Restricted

        Whether the environment is restricted to a specific set of users.

      • Optionalusers?: components["schemas"]["EnvironmentGroupUser"][]

        Users

        Users who can manage the environment while it is restricted, including organization and team admins who always have access. Empty when the environment is unrestricted.

    • EnvironmentGroups: {
          items: components["schemas"]["EnvironmentGroup"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      EnvironmentGroupsV1

      A page of environment groups.

      • items: components["schemas"]["EnvironmentGroup"][]

        Items

        Items in this page.

      • pagination: components["schemas"]["PaginationResponse"]

        Pagination metadata for the page.

    • EnvironmentGroupUser: { email: string | null; name: string | null; user_id: string }

      EnvironmentGroupUserV1

      A user referenced by an environment group's manage access.

      • email: string | null

        Email

        Email address of the user.

        null
        
      • name: string | null

        Name

        Display name of the user.

        null
        
      • user_id: string

        User Id

        Unique identifier for the user.

    • Environments: { environments: components["schemas"]["Environment"][] }

      EnvironmentsV1

      list of environments

    • EnvironmentTombstone: { deleted: boolean; model_id: string; name: string }

      EnvironmentTombstoneV1

      An environment tombstone.

      • deleted: boolean

        Deleted

        Whether the environment was deleted

      • model_id: string

        Model Id

        Unique identifier of the model

      • name: string

        Name

        Name of the environment

    • FileSummary: {
          file_type: string;
          modified: string;
          path: string;
          permissions: string;
          size_bytes: number;
      }

      FileSummary

      Information about a file in the cache.

      • file_type: string

        File Type

        Type of the file

      • modified: string

        Modified

        Last modification time of the file

      • path: string

        Path

        Relative path of the file in the cache

      • permissions: string

        Permissions

        Permissions of the file

      • size_bytes: number

        Size Bytes

        Size of the file in bytes

    • GatewayEvent: {
          apiKeyPrefix: string;
          externalEntityId: string;
          idempotencyKey: string;
          modelSlug: string;
          requestId: string;
          timestamp: string;
          tokens: components["schemas"]["GatewayEventTokens"];
          type: string;
      }

      GatewayEventV1

      • apiKeyPrefix: string

        Apikeyprefix

        API key prefix.

      • externalEntityId: string

        Externalentityid

        Calling group's external ID.

      • idempotencyKey: string

        Idempotencykey

        Deduplication key.

      • modelSlug: string

        Modelslug

        Served model.

      • requestId: string

        Requestid

        Inference request ID.

      • timestamp: string

        Timestamp

        Billing event time (ISO 8601, UTC).

      • tokens: components["schemas"]["GatewayEventTokens"]
      • type: string

        Type

        Event type.

        API_BILLING_USAGE
        
    • GatewayEventsResponse: {
          items: components["schemas"]["GatewayEvent"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      GatewayEventsResponseV1

    • GatewayEventTokens: { cachedInputTokens: number; inputTokens: number; outputTokens: number }

      GatewayEventTokensV1

      • cachedInputTokens: number

        Cachedinputtokens

        Cached input tokens.

      • inputTokens: number

        Inputtokens

        Cached and uncached input tokens.

      • outputTokens: number

        Outputtokens

        Output tokens.

    • GatewayKeyInfo: { name: string | null; prefix: string }

      GatewayKeyInfoV1

      • name: string | null

        Name

        Optional display name.

        null
        
      • prefix: string

        Prefix

        The prefix of the Model API key.

    • GatewayProvider:
          | "ANTHROPIC"
          | "OPENAI"
          | "XAI"
          | "BASETEN"
          | "BASETEN_MODEL_API"
          | "VERTEX"
          | "OPENAI_COMPATIBLE"

      GatewayProvider

      Customer-facing provider for an endpoint target.

      External providers resolve to a fixed upstream host + protocol adapter via
      ``external_provider_configs()``; ``BASETEN`` derives its host from the referenced oracle.
      
    • GcpOidcDockerAuth: { service_account: string; workload_identity_provider: string }

      GcpOidcDockerAuthV1

      GCP OIDC details for the registry.

      • service_account: string

        Service Account

        GCP service account name for OIDC authentication

      • workload_identity_provider: string

        Workload Identity Provider

        GCP workload identity provider for OIDC authentication

    • GcpServiceAccountJsonDockerAuth: { service_account_json_secret_ref: components["schemas"]["SecretReference"] }

      GcpServiceAccountJsonDockerAuthV1

      GCP details for the registry.

      • service_account_json_secret_ref: components["schemas"]["SecretReference"]

        Name of the service account secret

    • GetAuditLogsRequest: {
          chain_deployment_ids?: string[];
          cursor?: string | null;
          deployment_ids?: string[];
          direction?: components["schemas"]["AuditLogSortDirection"];
          end_epoch_millis?: number | null;
          environment_names?: string[];
          event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
          limit?: number;
          search?: string | null;
          sources?: components["schemas"]["AuditLogSource"][];
          start_epoch_millis?: number | null;
          user_ids?: string[];
      }
      • Optionalchain_deployment_ids?: string[]

        Chain Deployment Ids

        When set, returns only entries referencing one of these chain deployment IDs.

      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionaldeployment_ids?: string[]

        Deployment Ids

        When set, returns only entries referencing one of these model deployment IDs.

      • Optionaldirection?: components["schemas"]["AuditLogSortDirection"]

        Sort order by the time the action occurred. Defaults to DESC (newest first). Ignored when paginating with a cursor.

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds for the end of the window. Defaults to the current time.

      • Optionalenvironment_names?: string[]

        Environment Names

        When set, returns only entries for one of these environments.

      • Optionalevent_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][]

        Event Type Groups

        When set, returns only entries whose event type falls in one of these groups.

      • Optionallimit?: number

        Limit

        Maximum number of entries to return per page. Defaults to 20, and must be between 1 and 200.

      • Optionalsearch?: string | null

        Search

        Case-insensitive substring matched against resource names and IDs in the entry.

      • Optionalsources?: components["schemas"]["AuditLogSource"][]

        Sources

        When set, returns only entries issued from one of these surfaces.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds for the start of the window. Defaults to the beginning of the audit-log history.

      • Optionaluser_ids?: string[]

        User Ids

        When set, returns only entries whose acting user is one of these IDs.

    • GetAuthCodesResponse: { auth_codes: components["schemas"]["AuthCode"][] }

      GetAuthCodesResponseV1

      Response containing auth codes for all nodes of a training job's interactive sessions.

      • auth_codes: components["schemas"]["AuthCode"][]

        Auth Codes

        List of auth codes for each node that has an active interactive session.

    • GetBillingModelApisRequest: {
          api_key_prefixes?: string[];
          cursor?: string | null;
          end_date?: string | null;
          group_by?: components["schemas"]["ModelApiCostDimension"][];
          limit?: number;
          models?: string[];
          service_tiers?: string[];
          start_date?: string | null;
          user_ids?: string[];
      }
      • Optionalapi_key_prefixes?: string[]

        Api Key Prefixes

        Return only costs for these exact API key prefixes, repeated once per prefix.

      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionalend_date?: string | null

        End Date

        Exclusive UTC calendar day at the end of the query range. Defaults to the day after the current UTC date so current-day usage is included. The date range cannot exceed 90 days.

      • Optionalgroup_by?: components["schemas"]["ModelApiCostDimension"][]

        Group By

        Dimensions to break costs down by, repeated once per dimension: api_key_prefix, user, model, or service_tier. Each result represents one observed combination of the requested dimensions within that day. For example, grouping by api_key_prefix and user returns each API-key and user pair that had usage. Combinations without usage are omitted, so result counts can differ between days. Omit for daily organization totals.

      • Optionallimit?: number

        Limit

        Number of daily cost buckets to return. Defaults to 7; maximum 31.

      • Optionalmodels?: string[]

        Models

        Return only costs for these exact model identifiers, repeated once per model.

      • Optionalservice_tiers?: string[]

        Service Tiers

        Return only costs for these exact service tiers, repeated once per tier.

      • Optionalstart_date?: string | null

        Start Date

        Inclusive UTC calendar day at the start of the query range. Defaults to the previous UTC date, cannot be before 2026-08-05, and is ignored when you pass a cursor.

      • Optionaluser_ids?: string[]

        User Ids

        Return only costs attributed to these exact user IDs, repeated once per ID.

    • GetBillingUsageSummaryRequest: { end_date: string; start_date: string }
      • end_date: string

        End Date Format: date-time

        End date in ISO 8601 format (UTC). Date range cannot exceed 31 days.

      • start_date: string

        Start Date Format: date-time

        Start date (ISO 8601, UTC). Earliest queryable: 2026-01-01.

    • GetBlobCredentialsResponse: {
          creds: components["schemas"]["AWSCredentials"];
          s3_bucket: string;
          s3_key: string;
      }

      GetBlobCredentialsResponseV1

      Response to create a new set of credentials for blob upload.

      • creds: components["schemas"]["AWSCredentials"]

        The credentials to upload the blob to

      • s3_bucket: string

        S3 Bucket

        The S3 bucket to upload the blob to

      • s3_key: string

        S3 Key

        The S3 key to upload the blob to

    • GetCacheSummaryResponse: {
          file_summaries: components["schemas"]["FileSummary"][];
          project_id: string;
          timestamp: string;
      }

      GetCacheSummaryResponseV1

      Response for getting cache summary.

      • file_summaries: components["schemas"]["FileSummary"][]

        File Summaries

        List of files in the cache

      • project_id: string

        Project Id

        Project ID associated with the cache

      • timestamp: string

        Timestamp

        Timestamp when the cache summary was captured

    • GetChainsAuditLogsRequest: {
          chain_deployment_ids?: string[];
          cursor?: string | null;
          deployment_ids?: string[];
          direction?: components["schemas"]["AuditLogSortDirection"];
          end_epoch_millis?: number | null;
          environment_names?: string[];
          event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
          limit?: number;
          search?: string | null;
          sources?: components["schemas"]["AuditLogSource"][];
          start_epoch_millis?: number | null;
          user_ids?: string[];
      }
      • Optionalchain_deployment_ids?: string[]

        Chain Deployment Ids

        When set, returns only entries referencing one of these chain deployment IDs.

      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionaldeployment_ids?: string[]

        Deployment Ids

        When set, returns only entries referencing one of these model deployment IDs.

      • Optionaldirection?: components["schemas"]["AuditLogSortDirection"]

        Sort order by the time the action occurred. Defaults to DESC (newest first). Ignored when paginating with a cursor.

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds for the end of the window. Defaults to the current time.

      • Optionalenvironment_names?: string[]

        Environment Names

        When set, returns only entries for one of these environments.

      • Optionalevent_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][]

        Event Type Groups

        When set, returns only entries whose event type falls in one of these groups.

      • Optionallimit?: number

        Limit

        Maximum number of entries to return per page. Defaults to 20, and must be between 1 and 200.

      • Optionalsearch?: string | null

        Search

        Case-insensitive substring matched against resource names and IDs in the entry.

      • Optionalsources?: components["schemas"]["AuditLogSource"][]

        Sources

        When set, returns only entries issued from one of these surfaces.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds for the start of the window. Defaults to the beginning of the audit-log history.

      • Optionaluser_ids?: string[]

        User Ids

        When set, returns only entries whose acting user is one of these IDs.

    • GetChainsDeploymentsChainletsLogsRequest: {
          component?: string | null;
          direction?: components["schemas"]["SortOrder"] | null;
          end_epoch_millis?: number | null;
          excludes?: string[];
          includes?: string[];
          limit?: number | null;
          min_level?: components["schemas"]["LogLevel"] | null;
          replica?: string | null;
          request_id?: string | null;
          search_pattern?: string | null;
          start_epoch_millis?: number | null;
      }
      • Optionalcomponent?: string | null

        Component

        Only return logs from this component.

      • Optionaldirection?: components["schemas"]["SortOrder"] | null

        Sort order for logs

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds at which to stop fetching logs. Defaults to the current time.

      • Optionalexcludes?: string[]

        Excludes

        Case-sensitive substrings; lines containing any of these are dropped.

      • Optionalincludes?: string[]

        Includes

        Case-sensitive substrings that must all appear in the log message.

      • Optionallimit?: number | null

        Limit

        Limit of logs to fetch in a single request

      • Optionalmin_level?: components["schemas"]["LogLevel"] | null

        Minimum log severity to include. Omit to return all log lines, including lines that have no level. Any explicit value returns lines at or above that severity and drops lines without a level.

      • Optionalreplica?: string | null

        Replica

        Only return logs emitted by this replica (5-char short ID).

      • Optionalrequest_id?: string | null

        Request Id

        Only return logs tagged with this inference request ID.

      • Optionalsearch_pattern?: string | null

        Search Pattern

        RE2 regular expression matched against the log message. Prefer includes and excludes for plain substring matches.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds at which to start fetching logs. Defaults to 30 minutes before the end. The window from start to end must not exceed 7 days.

    • GetDeploymentLogsRequest: {
          component?: string | null;
          direction?: components["schemas"]["SortOrder"] | null;
          end_epoch_millis?: number | null;
          excludes?: string[];
          includes?: string[];
          limit?: number | null;
          min_level?: components["schemas"]["LogLevel"] | null;
          replica?: string | null;
          request_id?: string | null;
          search_pattern?: string | null;
          start_epoch_millis?: number | null;
      }

      GetDeploymentLogsRequestV1

      A request to fetch deployment logs.

      • Optionalcomponent?: string | null

        Component

        Only return logs from this component.

      • Optionaldirection?: components["schemas"]["SortOrder"] | null

        Sort order for logs

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds at which to stop fetching logs. Defaults to the current time.

      • Optionalexcludes?: string[]

        Excludes

        Case-sensitive substrings; lines containing any of these are dropped.

      • Optionalincludes?: string[]

        Includes

        Case-sensitive substrings that must all appear in the log message.

      • Optionallimit?: number | null

        Limit

        Limit of logs to fetch in a single request

      • Optionalmin_level?: components["schemas"]["LogLevel"] | null

        Minimum log severity to include. Omit to return all log lines, including lines that have no level. Any explicit value returns lines at or above that severity and drops lines without a level.

      • Optionalreplica?: string | null

        Replica

        Only return logs emitted by this replica (5-char short ID).

      • Optionalrequest_id?: string | null

        Request Id

        Only return logs tagged with this inference request ID.

      • Optionalsearch_pattern?: string | null

        Search Pattern

        RE2 regular expression matched against the log message. Prefer includes and excludes for plain substring matches.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds at which to start fetching logs. Defaults to 30 minutes before the end. The window from start to end must not exceed 7 days.

    • GetDeploymentPatchesStateResponse: {
          pending_patch_point:
              | components["schemas"]["DeploymentPatchPointWithHash"]
              | null;
          running_patch_point: components["schemas"]["DeploymentPatchPointWithHash"];
      }

      GetDeploymentPatchesStateResponseV1

      The patch state of the development deployment.

      The watch client computes its next patch off `pending_patch_point` when present,
      else `running_patch_point`.
      
      • pending_patch_point: components["schemas"]["DeploymentPatchPointWithHash"] | null

        The latest staged-but-unsynced patch point, or null when the deployment is recorded as caught up.

        null
        
      • running_patch_point: components["schemas"]["DeploymentPatchPointWithHash"]

        The patch point the deployment is recorded as running.

    • GetGatewayEventsRequest: {
          api_keys?: string[];
          cursor?: string | null;
          end_time?: string | null;
          external_entity_ids?: string[];
          limit?: number | null;
          start_time?: string | null;
      }
      • Optionalapi_keys?: string[]

        Api Keys

        Return only events for these API key prefixes, repeated once per prefix.

      • Optionalcursor?: string | null

        Cursor

        Next-page cursor. Other parameters are ignored.

      • Optionalend_time?: string | null

        End Time

        Exclusive end (ISO 8601, UTC). Defaults to now.

      • Optionalexternal_entity_ids?: string[]

        External Entity Ids

        Return only events for these external entity IDs, repeated once per ID.

      • Optionallimit?: number | null

        Limit

        Max events. Default 100, max 1000.

      • Optionalstart_time?: string | null

        Start Time

        Inclusive start (ISO 8601, UTC). Required without a cursor.

    • GetLogsResponse: { logs: components["schemas"]["Log"][] }

      GetLogsResponseV1

      A response to querying logs.

    • GetLoopsCapabilitiesResponse: { supported_models: components["schemas"]["SupportedModel"][] }

      GetLoopsCapabilitiesResponseV1

      Response for GET /v1/loops/capabilities.

      • supported_models: components["schemas"]["SupportedModel"][]

        Supported Models

        List of models available on the server.

    • GetLoopsCheckpointsFilesRequest: { page_size?: number; page_token?: number }
      • Optionalpage_size?: number

        Page Size

        Max files per page (default 1000).

      • Optionalpage_token?: number

        Page Token

        Offset into the file list (default 0).

    • GetLoopsCheckpointsRequest: {
          base_model?: string | null;
          checkpoint_path?: string | null;
          run_id?: string | null;
      }
      • Optionalbase_model?: string | null

        Base Model

        Filter by base model. Returns checkpoints across the caller's runs of this base model.

        Qwen/Qwen3-8B
        
      • Optionalcheckpoint_path?: string | null

        Checkpoint Path

        bt:// URI of a Loops checkpoint. Form: bt://loops:<run_id>/(weights|sampler_weights)/<checkpoint_name>.

        bt://loops:k4q95w5/sampler_weights/step-100
        
      • Optionalrun_id?: string | null

        Run Id

        Filter by run ID. Returns all checkpoints saved by the run.

        k4q95w5
        
    • GetLoopsDeploymentMetricsRequest: {
          end_epoch_millis?: number | null;
          start_epoch_millis?: number | null;
          step_seconds?: number | null;
          time_divisor_seconds?: number | null;
      }

      GetLoopsDeploymentMetricsRequestV1

      Time-range request for trainer deployment metrics.

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch millis to end fetching metrics.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch millis to start fetching metrics.

      • Optionalstep_seconds?: number | null

        Step Seconds

        Resolution of the returned series, in seconds. When omitted, a step is derived from the time range so large windows return fewer points.

      • Optionaltime_divisor_seconds?: number | null

        Time Divisor Seconds

        Unit of time for request-volume metrics, in seconds (e.g. 60 for requests/minute). Defaults to per-second.

    • GetLoopsDeploymentMetricsResponse: {
          deployment_id: string;
          metrics: components["schemas"]["LoopsDeploymentMetrics"];
      }

      GetLoopsDeploymentMetricsResponseV1

      Response for POST /v1/loops/deployments/<id>/metrics.

      • deployment_id: string

        Deployment Id

        The trainer deployment ID.

      • metrics: components["schemas"]["LoopsDeploymentMetrics"]

        Metrics for the deployment.

    • GetLoopsDeploymentResponse: { deployment: components["schemas"]["LoopsDeployment"] }

      GetLoopsDeploymentResponseV1

      Response for GET /v1/loops/deployments/<deployment_id>.

    • GetLoopsDeploymentsDebugArchiveFilesRequest: { page_size?: number; page_token?: string | null }
      • Optionalpage_size?: number

        Page Size

        Max files per page (default and maximum 1000).

      • Optionalpage_token?: string | null

        Page Token

        Opaque token for the next page.

    • GetLoopsDeploymentsLogsRequest: {
          direction?: components["schemas"]["SortOrder"] | null;
          end_epoch_millis?: number | null;
          limit?: number | null;
          min_level?: components["schemas"]["LogLevel"] | null;
          start_epoch_millis?: number | null;
      }
      • Optionaldirection?: components["schemas"]["SortOrder"] | null

        Sort order for logs

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds at which to stop fetching logs. Defaults to the current time.

      • Optionallimit?: number | null

        Limit

        Limit of logs to fetch in a single request

      • Optionalmin_level?: components["schemas"]["LogLevel"] | null

        Minimum log severity to include. Omit to return all log lines, including lines that have no level. Any explicit value returns lines at or above that severity and drops lines without a level.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds at which to start fetching logs. Defaults to 30 minutes before the end. The window from start to end must not exceed 7 days.

    • GetLoopsDeploymentsRequest: { scope?: string | null }
      • Optionalscope?: string | null

        Scope

        Defaults to the caller's own deployments; pass 'org' to list every deployment in the caller's organization.

        org
        
    • GetLoopsRunResponse: { run: components["schemas"]["LoopsRun"] }

      GetLoopsRunResponseV1

      Response for GET /v1/loops/runs/<run_id>.

    • GetLoopsRunsRequest: { base_model?: string | null; run_id?: string | null; scope?: string | null }
      • Optionalbase_model?: string | null

        Base Model

        Filter runs by base model name.

        Qwen/Qwen3-8B
        
      • Optionalrun_id?: string | null

        Run Id

        Filter by run ID.

        k4q95w5
        
      • Optionalscope?: string | null

        Scope

        Defaults to the caller's own runs; pass 'org' to list every run in the caller's organization.

        org
        
    • GetLoopsSamplerResponse: { sampler: components["schemas"]["LoopsSampler"] }

      GetLoopsSamplerResponseV1

      Response for GET /v1/loops/samplers/<sampler_id>.

    • GetLoopsSamplersRequest: { scope?: string | null }
      • Optionalscope?: string | null

        Scope

        Defaults to the caller's own samplers; pass 'org' to include samplers owned by other users in the caller's organization.

        org
        
    • GetLoopsSessionResponse: { session: components["schemas"]["LoopsSession"] }

      GetLoopsSessionResponseV1

      Response for GET /v1/loops/sessions/<session_id>.

    • GetLoopsUserConfigResponse: { user_config: components["schemas"]["LoopsUserConfig"] }

      GetLoopsUserConfigResponseV1

      Response for GET /v1/loops/user_config.

      • user_config: components["schemas"]["LoopsUserConfig"]

        The caller's Loops user config.

    • GetModelApisRequest: { added_only?: boolean; cursor?: string | null; limit?: number }
      • Optionaladded_only?: boolean

        Added Only

        When true, restrict the result to Model APIs the workspace has added. Defaults to the full visible catalog.

      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionallimit?: number

        Limit

        Maximum number of items to return.

    • GetModelApisUsageRequest: {
          api_keys?: string[];
          bucket_width?: components["schemas"]["BucketWidth"];
          cursor?: string | null;
          end_time?: string | null;
          group_by?: components["schemas"]["UsageDimension"][];
          limit?: number | null;
          models?: string[];
          start_time?: string | null;
          user_ids?: string[];
      }
      • Optionalapi_keys?: string[]

        Api Keys

        Return only usage for these API key prefixes, repeated once per prefix.

      • Optionalbucket_width?: components["schemas"]["BucketWidth"]

        Width of each time bucket: 1m, 1h, or 1d. Defaults to 1d.

      • Optionalcursor?: string | null

        Cursor

        Opaque cursor from the pagination.cursor field of a previous response

      • Optionalend_time?: string | null

        End Time

        End of the query range (ISO 8601, UTC), exclusive. Defaults to the current time.

      • Optionalgroup_by?: components["schemas"]["UsageDimension"][]

        Group By

        Dimensions to break usage down by, repeated once per dimension: api_key, user, model. Defaults to model.

      • Optionallimit?: number | null

        Limit

        Number of time buckets to return. Defaults and maximums depend on bucket_width: 1d defaults to 7 and allows 31, 1h defaults to 24 and allows 168, 1m defaults to 60 and allows 1440.

      • Optionalmodels?: string[]

        Models

        Return only usage for these models, repeated once per model.

      • Optionalstart_time?: string | null

        Start Time

        Start of the query range (ISO 8601, UTC), inclusive. Snapped down to the start of its bucket. Required on the first page, and ignored when you pass a cursor.

      • Optionaluser_ids?: string[]

        User Ids

        Return only usage attributed to these user IDs, repeated once per ID.

    • GetModelMetricsResponse: {
          end_epoch_millis: number;
          metric_descriptors: components["schemas"]["ModelMetricDescriptor"][];
          metric_values: components["schemas"]["ModelMetricValueSet"][];
          mode: components["schemas"]["ModelMetricMode"];
          start_epoch_millis: number;
          step_seconds: number | null;
      }

      GetModelMetricsResponseV1

      Model metrics over a time window, index-mapped: metric descriptors appear once in metric_descriptors; each value set's values are aligned to that order.

      • end_epoch_millis: number

        End Epoch Millis

        End of the returned window.

      • metric_descriptors: components["schemas"]["ModelMetricDescriptor"][]

        Metric Descriptors

        Descriptors for each metric; position defines the values index.

      • metric_values: components["schemas"]["ModelMetricValueSet"][]

        Metric Values

        Metric values per time step covering the window. In summary mode this always contains exactly one value set spanning the whole window.

      • mode: components["schemas"]["ModelMetricMode"]

        The aggregation mode used.

      • start_epoch_millis: number

        Start Epoch Millis

        Start of the returned window.

      • step_seconds: number | null

        Step Seconds

        Seconds per step; populated only in SERIES mode, null otherwise.

    • GetModelsAuditLogsRequest: {
          chain_deployment_ids?: string[];
          cursor?: string | null;
          deployment_ids?: string[];
          direction?: components["schemas"]["AuditLogSortDirection"];
          end_epoch_millis?: number | null;
          environment_names?: string[];
          event_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][];
          limit?: number;
          search?: string | null;
          sources?: components["schemas"]["AuditLogSource"][];
          start_epoch_millis?: number | null;
          user_ids?: string[];
      }
      • Optionalchain_deployment_ids?: string[]

        Chain Deployment Ids

        When set, returns only entries referencing one of these chain deployment IDs.

      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionaldeployment_ids?: string[]

        Deployment Ids

        When set, returns only entries referencing one of these model deployment IDs.

      • Optionaldirection?: components["schemas"]["AuditLogSortDirection"]

        Sort order by the time the action occurred. Defaults to DESC (newest first). Ignored when paginating with a cursor.

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds for the end of the window. Defaults to the current time.

      • Optionalenvironment_names?: string[]

        Environment Names

        When set, returns only entries for one of these environments.

      • Optionalevent_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][]

        Event Type Groups

        When set, returns only entries whose event type falls in one of these groups.

      • Optionallimit?: number

        Limit

        Maximum number of entries to return per page. Defaults to 20, and must be between 1 and 200.

      • Optionalsearch?: string | null

        Search

        Case-insensitive substring matched against resource names and IDs in the entry.

      • Optionalsources?: components["schemas"]["AuditLogSource"][]

        Sources

        When set, returns only entries issued from one of these surfaces.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds for the start of the window. Defaults to the beginning of the audit-log history.

      • Optionaluser_ids?: string[]

        User Ids

        When set, returns only entries whose acting user is one of these IDs.

    • GetModelsDeploymentsConfigRequest: { output_format?: components["schemas"]["DeploymentConfigOutputFormat"] }
      • Optionaloutput_format?: components["schemas"]["DeploymentConfigOutputFormat"]

        'raw': verbatim config.yaml with comments (not available for deployments created before 2026-04-30). 'parsed': dict with server-side defaults applied (always available). 'both': both fields populated.

    • GetModelsDeploymentsLogsRequest: {
          component?: string | null;
          direction?: components["schemas"]["SortOrder"] | null;
          end_epoch_millis?: number | null;
          excludes?: string[];
          includes?: string[];
          limit?: number | null;
          min_level?: components["schemas"]["LogLevel"] | null;
          replica?: string | null;
          request_id?: string | null;
          search_pattern?: string | null;
          start_epoch_millis?: number | null;
      }
      • Optionalcomponent?: string | null

        Component

        Only return logs from this component.

      • Optionaldirection?: components["schemas"]["SortOrder"] | null

        Sort order for logs

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds at which to stop fetching logs. Defaults to the current time.

      • Optionalexcludes?: string[]

        Excludes

        Case-sensitive substrings; lines containing any of these are dropped.

      • Optionalincludes?: string[]

        Includes

        Case-sensitive substrings that must all appear in the log message.

      • Optionallimit?: number | null

        Limit

        Limit of logs to fetch in a single request

      • Optionalmin_level?: components["schemas"]["LogLevel"] | null

        Minimum log severity to include. Omit to return all log lines, including lines that have no level. Any explicit value returns lines at or above that severity and drops lines without a level.

      • Optionalreplica?: string | null

        Replica

        Only return logs emitted by this replica (5-char short ID).

      • Optionalrequest_id?: string | null

        Request Id

        Only return logs tagged with this inference request ID.

      • Optionalsearch_pattern?: string | null

        Search Pattern

        RE2 regular expression matched against the log message. Prefer includes and excludes for plain substring matches.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds at which to start fetching logs. Defaults to 30 minutes before the end. The window from start to end must not exceed 7 days.

    • GetModelsDeploymentsMetricsRequest: {
          end_epoch_millis?: number | null;
          metrics?: string[];
          mode?: components["schemas"]["ModelMetricMode"];
          start_epoch_millis?: number | null;
      }
      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch millis timestamp to end fetching metrics. Defaults to the current time. The window between start and end must not exceed 7 days.

      • Optionalmetrics?: string[]

        Metrics

        Names of the metrics to return; see https://docs.baseten.co/observability/export-metrics/supported-metrics for the available names. When omitted, a default set is returned: baseten_replicas_active, baseten_inference_requests_total, and baseten_end_to_end_response_time_seconds. Unknown names are rejected; valid names that do not apply are omitted from the response.

      • Optionalmode?: components["schemas"]["ModelMetricMode"]

        'CURRENT': a single instantaneous snapshot at now; start/end must be omitted. 'SUMMARY': a single value set aggregating the whole window. 'SERIES': evenly-spaced value sets across the window, with the step derived from the window duration.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch millis timestamp to start fetching metrics. Defaults to one hour before the end.

    • GetModelsDeploymentsRequest: { name?: string | null }
      • Optionalname?: string | null

        Name

        When set, returns only the deployment with this exact name, if any.

    • GetModelsEnvironmentsLogsRequest: {
          component?: string | null;
          direction?: components["schemas"]["SortOrder"] | null;
          end_epoch_millis?: number | null;
          excludes?: string[];
          includes?: string[];
          limit?: number | null;
          min_level?: components["schemas"]["LogLevel"] | null;
          replica?: string | null;
          request_id?: string | null;
          search_pattern?: string | null;
          start_epoch_millis?: number | null;
      }
      • Optionalcomponent?: string | null

        Component

        Only return logs from this component.

      • Optionaldirection?: components["schemas"]["SortOrder"] | null

        Sort order for logs

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds at which to stop fetching logs. Defaults to the current time.

      • Optionalexcludes?: string[]

        Excludes

        Case-sensitive substrings; lines containing any of these are dropped.

      • Optionalincludes?: string[]

        Includes

        Case-sensitive substrings that must all appear in the log message.

      • Optionallimit?: number | null

        Limit

        Limit of logs to fetch in a single request

      • Optionalmin_level?: components["schemas"]["LogLevel"] | null

        Minimum log severity to include. Omit to return all log lines, including lines that have no level. Any explicit value returns lines at or above that severity and drops lines without a level.

      • Optionalreplica?: string | null

        Replica

        Only return logs emitted by this replica (5-char short ID).

      • Optionalrequest_id?: string | null

        Request Id

        Only return logs tagged with this inference request ID.

      • Optionalsearch_pattern?: string | null

        Search Pattern

        RE2 regular expression matched against the log message. Prefer includes and excludes for plain substring matches.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds at which to start fetching logs. Defaults to 30 minutes before the end. The window from start to end must not exceed 7 days.

    • GetModelsEnvironmentsMetricsRequest: {
          end_epoch_millis?: number | null;
          metrics?: string[];
          mode?: components["schemas"]["ModelMetricMode"];
          start_epoch_millis?: number | null;
      }
      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch millis timestamp to end fetching metrics. Defaults to the current time. The window between start and end must not exceed 7 days.

      • Optionalmetrics?: string[]

        Metrics

        Names of the metrics to return; see https://docs.baseten.co/observability/export-metrics/supported-metrics for the available names. When omitted, a default set is returned: baseten_replicas_active, baseten_inference_requests_total, and baseten_end_to_end_response_time_seconds. Unknown names are rejected; valid names that do not apply are omitted from the response.

      • Optionalmode?: components["schemas"]["ModelMetricMode"]

        'CURRENT': a single instantaneous snapshot at now; start/end must be omitted. 'SUMMARY': a single value set aggregating the whole window. 'SERIES': evenly-spaced value sets across the window, with the step derived from the window duration.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch millis timestamp to start fetching metrics. Defaults to one hour before the end.

    • GetModelsRequest: { name?: string | null }
      • Optionalname?: string | null

        Name

        When set, returns only models with this exact name, if any. On a team-scoped route this matches at most one model; on the org-wide route it may match models in multiple teams, since names are unique only within a team.

    • GetTeamsLoopsRunsRequest: { base_model?: string | null; run_id?: string | null; scope?: string | null }
      • Optionalbase_model?: string | null

        Base Model

        Filter runs by base model name.

        Qwen/Qwen3-8B
        
      • Optionalrun_id?: string | null

        Run Id

        Filter by run ID.

        k4q95w5
        
      • Optionalscope?: string | null

        Scope

        Defaults to the caller's own runs; pass 'org' to list every run in the caller's organization.

        org
        
    • GetTeamsLoopsSamplersRequest: { scope?: string | null }
      • Optionalscope?: string | null

        Scope

        Defaults to the caller's own samplers; pass 'org' to include samplers owned by other users in the caller's organization.

        org
        
    • GetTeamsModelsRequest: { name?: string | null }
      • Optionalname?: string | null

        Name

        When set, returns only models with this exact name, if any. On a team-scoped route this matches at most one model; on the org-wide route it may match models in multiple teams, since names are unique only within a team.

    • GetTeamsRequest: { name?: string | null }
      • Optionalname?: string | null

        Name

        When set, returns only the team with this exact name, if any.

    • GetTrainingGpuCapacityResponse: {
          gpu_capacities: components["schemas"]["TrainingGpuCapacityItem"][];
          team_gpu_capacities?: components["schemas"]["TeamTrainingGpuCapacityItem"][];
      }

      GetTrainingGpuCapacityResponseV1

      Response for the training GPU capacity endpoint.

      • gpu_capacities: components["schemas"]["TrainingGpuCapacityItem"][]

        Gpu Capacities

        Org-level GPU capacity limits and current usage per GPU type

      • Optionalteam_gpu_capacities?: components["schemas"]["TeamTrainingGpuCapacityItem"][]

        Team Gpu Capacities

        Per-team GPU capacity limits and current usage per GPU type

    • GetTrainingJobCheckpointFilesResponse: {
          next_page_token: number | null;
          presigned_urls: components["schemas"]["CheckpointFile"][];
          total_count: number;
      }

      GetTrainingJobCheckpointFilesResponseV1

      A response to fetch presigned URLs for checkpoint files of a training job.

      • next_page_token: number | null

        Next Page Token

        Token to use for fetching the next page of results. None when there are no more results.

        null
        
      • presigned_urls: components["schemas"]["CheckpointFile"][]

        Presigned Urls

        List of presigned URLs for checkpoint files.

      • total_count: number

        Total Count

        Total number of checkpoint files available.

    • GetTrainingJobCheckpointsResponse: {
          checkpoints: components["schemas"]["TrainingJobCheckpoint"][];
          training_job: components["schemas"]["TrainingJob"];
      }

      GetTrainingJobCheckpointsResponseV1

      A response to fetch checkpoints for a training job.

      • checkpoints: components["schemas"]["TrainingJobCheckpoint"][]

        Checkpoints

        The checkpoints for the training job.

      • training_job: components["schemas"]["TrainingJob"]

        The training job.

    • GetTrainingJobLogsRequest: {
          direction?: components["schemas"]["SortOrder"] | null;
          end_epoch_millis?: number | null;
          limit?: number | null;
          min_level?: components["schemas"]["LogLevel"] | null;
          start_epoch_millis?: number | null;
      }

      GetTrainingJobLogsRequestV1

      A request to fetch training logs.

      • Optionaldirection?: components["schemas"]["SortOrder"] | null

        Sort order for logs

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds at which to stop fetching logs. Defaults to the current time.

      • Optionallimit?: number | null

        Limit

        Limit of logs to fetch in a single request

      • Optionalmin_level?: components["schemas"]["LogLevel"] | null

        Minimum log severity to include. Omit to return all log lines, including lines that have no level. Any explicit value returns lines at or above that severity and drops lines without a level.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds at which to start fetching logs. Defaults to 30 minutes before the end. The window from start to end must not exceed 7 days.

    • GetTrainingJobMetricsRequest: {
          end_epoch_millis?: number | null;
          start_epoch_millis?: number | null;
          step_seconds?: number | null;
      }

      GetTrainingJobMetricsRequestV1

      A request to fetch metrics. Allows the user to request metrics over a period of time.

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch millis timestamp to end fetching metrics

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch millis timestamp to start fetching metrics.

      • Optionalstep_seconds?: number | null

        Step Seconds

        Resolution of the returned series, in seconds. When omitted, a step is derived from the time range so large windows return fewer points.

    • GetTrainingJobMetricsResponse: {
          cache: components["schemas"]["StorageMetrics"] | null;
          cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
          cpu_usage: components["schemas"]["TrainingJobMetric"][];
          ephemeral_storage: components["schemas"]["StorageMetrics"];
          gpu_memory_usage_bytes: {
              [key: string]: { timestamp: string; value: number }[];
          };
          gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
          per_node_metrics: components["schemas"]["TrainingJobNodeMetrics"][];
          training_job: components["schemas"]["TrainingJob"];
      }

      GetTrainingJobMetricsResponseV1

      A response to fetch training job metrics. The outer list for each metric represents that metric across time.

      • cache: components["schemas"]["StorageMetrics"] | null

        The storage usage for the read-write cache.

      • cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][]

        Cpu Memory Usage Bytes

        The CPU memory usage for the training job. For multinode jobs, this is the CPU memory usage of the leader unless specified otherwise.

      • cpu_usage: components["schemas"]["TrainingJobMetric"][]

        Cpu Usage

        The CPU usage measured in cores. For multinode jobs, this is the CPU usage of the leader unless specified otherwise.

      • ephemeral_storage: components["schemas"]["StorageMetrics"]

        The storage usage for the ephemeral storage. For multinode jobs, this is the ephemeral storage usage of the leader unless specified otherwise.

      • gpu_memory_usage_bytes: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Memory Usage Bytes

        A map of GPU rank to memory usage for the training job. For multinode jobs, this is the memory usage of the leader unless specified otherwise.

      • gpu_utilization: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Utilization

        A map of GPU rank to fractional GPU utilization. For multinode jobs, this is the GPU utilization of the leader unless specified otherwise.

      • per_node_metrics: components["schemas"]["TrainingJobNodeMetrics"][]

        Per Node Metrics

        The metrics for each node in the training job.

      • training_job: components["schemas"]["TrainingJob"]

        The training job.

    • GetTrainingJobQueueContextResponse: {
          active_at_submit: components["schemas"]["ActiveJobAtSubmit"][];
          events: components["schemas"]["QueueEvent"][];
          events_window_end: string;
          gpu_type: string;
          org_capacity: components["schemas"]["CapacityAtSubmit"] | null;
          pending_ahead_at_submit: components["schemas"]["PendingJobAheadAtSubmit"][];
          pending_seconds: number | null;
          released_at: string | null;
          requested_gpus: number;
          submitted_at: string;
          target_job_id: string;
          target_job_name: string | null;
          team_capacity: components["schemas"]["CapacityAtSubmit"] | null;
      }

      GetTrainingJobQueueContextResponseV1

      Read-only diagnostic for a training job's PENDING window.

      Returns the (org, gpu_type) capacity pool the job was gated by, jobs that
      were holding GPU capacity in that pool when this job was submitted, and
      every status event in [submitted_at, released_at] for those jobs (or up to
      "now" if the target is still PENDING).
      
      • active_at_submit: components["schemas"]["ActiveJobAtSubmit"][]

        Active At Submit

        Jobs in the same (org, gpu_type) pool that were holding capacity at submitted_at

      • events: components["schemas"]["QueueEvent"][]

        Events

        Every status event in [submitted_at, events_window_end] for the target job, every job in active_at_submit, and every job in pending_ahead_at_submit, oldest first.

      • events_window_end: string

        Events Window End Format: date-time

        released_at if set, else 'now' (events ongoing)

      • gpu_type: string

        Gpu Type

        GPU type the target requested

      • org_capacity: components["schemas"]["CapacityAtSubmit"] | null

        Org-level cap for (org, gpu_type). None if no cap is configured.

        null
        
      • pending_ahead_at_submit: components["schemas"]["PendingJobAheadAtSubmit"][]

        Pending Ahead At Submit

        PENDING jobs in the same (org, gpu_type) pool that were ahead of the target in dequeue FIFO order at submitted_at (priority DESC then created ASC). These also block the target's release.

      • pending_seconds: number | null

        Pending Seconds

        released_at - submitted_at in seconds. None if still PENDING.

        null
        
      • released_at: string | null

        Released At

        When the job's TRAINING_JOB_CREATED status was set, i.e. the moment it was released from PENDING. None if still PENDING.

        null
        
      • requested_gpus: number

        Requested Gpus

        GPUs the target requested (gpu_count * effective_node_count)

      • submitted_at: string

        Submitted At Format: date-time

        When the job row was inserted (= API POST time)

      • target_job_id: string

        Target Job Id

        Hashid of the target training job

      • target_job_name: string | null

        Target Job Name

        Target job's name

        null
        
      • team_capacity: components["schemas"]["CapacityAtSubmit"] | null

        Team-level cap for (team, gpu_type). None if no team cap is configured.

        null
        
    • GetTrainingJobResponse: {
          training_job: components["schemas"]["TrainingJob"];
          training_project: components["schemas"]["TrainingProject"];
      }

      GetTrainingJobResponseV1

      A response to fetch a training job.

    • GetTrainingProjectResponse: { training_project: components["schemas"]["TrainingProject"] }

      GetTrainingProjectResponseV1

      A response to getting a training project.

    • GetTrainingProjectsJobsCheckpointFilesRequest: { page_size?: number; page_token?: number }
      • Optionalpage_size?: number

        Page Size

        Max files per page (default 1000).

      • Optionalpage_token?: number

        Page Token

        Offset into the file list (default 0).

    • GetTrainingProjectsJobsLogsRequest: {
          direction?: components["schemas"]["SortOrder"] | null;
          end_epoch_millis?: number | null;
          limit?: number | null;
          min_level?: components["schemas"]["LogLevel"] | null;
          start_epoch_millis?: number | null;
      }
      • Optionaldirection?: components["schemas"]["SortOrder"] | null

        Sort order for logs

      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch milliseconds at which to stop fetching logs. Defaults to the current time.

      • Optionallimit?: number | null

        Limit

        Limit of logs to fetch in a single request

      • Optionalmin_level?: components["schemas"]["LogLevel"] | null

        Minimum log severity to include. Omit to return all log lines, including lines that have no level. Any explicit value returns lines at or above that severity and drops lines without a level.

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch milliseconds at which to start fetching logs. Defaults to 30 minutes before the end. The window from start to end must not exceed 7 days.

    • GetTrainingProjectsJobsMetricsRequest: {
          end_epoch_millis?: number | null;
          start_epoch_millis?: number | null;
          step_seconds?: number | null;
      }
      • Optionalend_epoch_millis?: number | null

        End Epoch Millis

        Epoch millis timestamp to end fetching metrics

      • Optionalstart_epoch_millis?: number | null

        Start Epoch Millis

        Epoch millis timestamp to start fetching metrics.

      • Optionalstep_seconds?: number | null

        Step Seconds

        Resolution of the returned series, in seconds. When omitted, a step is derived from the time range so large windows return fewer points.

    • GetUsersRequest: { cursor?: string | null; email?: string | null; limit?: number }
      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionalemail?: string | null

        Email

        When set, returns only users with this exact email, if any.

      • Optionallimit?: number

        Limit

        Maximum number of items to return.

    • GetVolumesNamespacesRequest: { cursor?: string | null; limit?: number }
      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionallimit?: number

        Limit

        Maximum number of namespaces to return.

    • GetVolumesRequest: { cursor?: string | null; limit?: number; namespace: string }
      • Optionalcursor?: string | null

        Cursor

        Opaque cursor returned by a previous page. Omit to fetch the first page.

      • Optionallimit?: number

        Limit

        Maximum number of volumes to return.

      • namespace: string

        Namespace

        Namespace to list volumes in. Required, because the volume service has no cross-namespace inventory.

    • GetVolumesVersionsRequest: { include_tombstoned?: boolean }
      • Optionalinclude_tombstoned?: boolean

        Include Tombstoned

        Whether to include deleted versions. A deleted version carries a TOMBSTONED lifecycle and stays restorable until its recovery deadline passes.

    • GitInfo: {
          commits_since_tag: number | null;
          has_uncommitted_changes: boolean;
          latest_commit_sha: string;
          latest_tag: string | null;
      }

      GitInfo

      • commits_since_tag: number | null

        Commits Since Tag

      • has_uncommitted_changes: boolean

        Has Uncommitted Changes

      • latest_commit_sha: string

        Latest Commit Sha

      • latest_tag: string | null

        Latest Tag

    • Group: {
          created_at: string;
          effective_models?: components["schemas"]["EffectiveModelConfig"][];
          hierarchy: components["schemas"]["GroupHierarchy"];
          id: string;
          metadata: components["schemas"]["GroupMetadata"];
          models?: components["schemas"]["ModelConfig"][];
      }

      GroupV1

      • created_at: string

        Created At Format: date-time

        When this group was created.

      • Optionaleffective_models?: components["schemas"]["EffectiveModelConfig"][]

        Effective Models

      • hierarchy: components["schemas"]["GroupHierarchy"]

        Parent linkage and limit enforcement mode. Parent is null for root groups.

      • id: string

        Id

        Internal Baseten ID for the group.

      • metadata: components["schemas"]["GroupMetadata"]

        Group identity + display metadata.

      • Optionalmodels?: components["schemas"]["ModelConfig"][]

        Models

    • GroupHierarchy: {
          limit_enforcement: components["schemas"]["LimitEnforcement"];
          parent_group_id: string | null;
      }

      GroupHierarchyV1

      • limit_enforcement: components["schemas"]["LimitEnforcement"]
        CASCADING
        
        INDEPENDENT
        
      • parent_group_id: string | null

        Parent Group Id

        null
        
        abc123
        
    • GroupMetadata: { external_entity_id: string; name?: string | null }

      GroupMetadataV1

      • external_entity_id: string

        External Entity Id

        External-system identifier for this group. Unique within the caller's org.

        cust_42
        
      • Optionalname?: string | null

        Name

        Optional display name for the group.

        Acme prod
        
    • GroupsResponse: {
          items: components["schemas"]["Group"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      GroupsResponseV1

    • InferenceVolumeByStatusDatapoint: {
          status_2xx: number;
          status_4xx: number;
          status_5xx: number;
          timestamp: string;
      }

      InferenceVolumeByStatusDatapointV1

      Request rate split by HTTP response code class.

      • status_2xx: number

        Status 2Xx

        2xx requests per second.

      • status_4xx: number

        Status 4Xx

        4xx requests per second.

      • status_5xx: number

        Status 5Xx

        5xx requests per second.

      • timestamp: string

        Timestamp Format: date-time

        ISO 8601 timestamp.

    • InProgressPromotion: {
          error_message: string | null;
          percent_traffic_to_new_version: number;
          rolling_deploy: boolean | null;
          status: components["schemas"]["InProgressPromotionStatus"];
      }

      InProgressPromotionV1

      Details of an in-progress promotion.

      • error_message: string | null

        Error Message

        Error message if promotion failed

        null
        
      • percent_traffic_to_new_version: number

        Percent Traffic To New Version

        Percentage of traffic routed to the candidate deployment

      • rolling_deploy: boolean | null

        Rolling Deploy

        Whether this is a rolling deploy

        null
        
      • status: components["schemas"]["InProgressPromotionStatus"]

        Status of the promotion

    • InProgressPromotionStatus:
          | "RELEASING"
          | "RAMPING_UP"
          | "RAMPING_DOWN"
          | "PAUSED"
          | "SUCCEEDED"
          | "FAILED"
          | "CANCELED"

      InProgressPromotionStatusV1

    • InstanceType: {
          gpu_count: number;
          gpu_memory_limit_mib: number | null;
          gpu_type: string | null;
          id: string;
          memory_limit_mib: number;
          millicpu_limit: number;
          name: string;
      }

      InstanceTypeV1

      An instance type.

      • gpu_count: number

        Gpu Count

        Number of GPUs on the instance type

      • gpu_memory_limit_mib: number | null

        Gpu Memory Limit Mib

        Memory limit of the GPU on the instance type in Mebibytes

      • gpu_type: string | null

        Gpu Type

        Type of GPU on the instance type

      • id: string

        Id

        Identifier string for the instance type

      • memory_limit_mib: number

        Memory Limit Mib

        Memory limit of the instance type in Mebibytes

      • millicpu_limit: number

        Millicpu Limit

        CPU limit of the instance type in millicpu

      • name: string

        Name

        Display name of the instance type

    • InstanceTypePrices: { instance_types: components["schemas"]["InstanceTypeWithPrice"][] }

      InstanceTypePricesV1

      A list of instance types.

    • InstanceTypes: { instance_types: components["schemas"]["InstanceType"][] }

      InstanceTypesV1

      A list of instance types.

    • InstanceTypeWithPrice: { instance_type: components["schemas"]["InstanceType"]; price: number }

      InstanceTypeWithPriceV1

      • instance_type: components["schemas"]["InstanceType"]

        Instance type properties.

      • price: number

        Price

        Usage price in USD / minute.

    • InteractiveSession: {
          auth_code: string | null;
          auth_code_generated_at: string | null;
          auth_provider: string;
          auth_url: string | null;
          authenticated_at: string | null;
          expires_at: string | null;
          id: string;
          pod_name: string;
          session_provider: string;
          timeout_minutes: number;
          trigger: string;
          tunnel_name: string | null;
          working_directory: string | null;
      }

      InteractiveSessionV1

      Representation of a training job interactive session.

      • auth_code: string | null

        Auth Code

        The device authentication code.

        null
        
      • auth_code_generated_at: string | null

        Auth Code Generated At

        When the auth code was generated.

        null
        
      • auth_provider: string

        Auth Provider

        The authentication provider for the session.

      • auth_url: string | null

        Auth Url

        URL where the user should enter the auth code.

        null
        
      • authenticated_at: string | null

        Authenticated At

        When the session was authenticated.

        null
        
      • expires_at: string | null

        Expires At

        When the session expires, in ISO 8601 format.

        null
        
      • id: string

        Id

        Unique identifier of the interactive session.

      • pod_name: string

        Pod Name

        Pod name / node rank for the session.

      • session_provider: string

        Session Provider

        The IDE client for the session.

      • timeout_minutes: number

        Timeout Minutes

        Minutes before the session times out.

      • trigger: string

        Trigger

        When the interactive session is created.

      • tunnel_name: string | null

        Tunnel Name

        The tunnel name for the session.

        null
        
      • working_directory: string | null

        Working Directory

        The working directory of the session.

        null
        
    • InteractiveSessionConfig: {
          auth_provider?: components["schemas"]["V1InteractiveSessionAuthProvider"];
          session_provider?: components["schemas"]["V1InteractiveSessionProvider"];
          timeout_minutes?: number;
          trigger?: components["schemas"]["V1InteractiveSessionTrigger"];
      }

      InteractiveSessionConfigV1

      Configuration for interactive debugging sessions on training jobs.

      • Optionalauth_provider?: components["schemas"]["V1InteractiveSessionAuthProvider"]

        The authentication provider for the interactive session.

      • Optionalsession_provider?: components["schemas"]["V1InteractiveSessionProvider"]

        The IDE client for the interactive session.

      • Optionaltimeout_minutes?: number

        Timeout Minutes

        Number of minutes before the interactive session times out.

        480
        
        1440
        
        10080
        
      • Optionaltrigger?: components["schemas"]["V1InteractiveSessionTrigger"]

        When to create the interactive session. 'on_startup' creates on job start, 'on_failure' creates on job failure, 'on_demand' bypasses automatic session creation.

    • KeysForGroupResponse: {
          items: components["schemas"]["GatewayKeyInfo"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      KeysForGroupResponseV1

    • LibraryListing: {
          closed_source: boolean;
          created_at: string;
          display_name: string;
          is_public: boolean;
          metadata: components["schemas"]["LibraryListingMetadata"] | null;
          modified_at: string;
          trending: boolean | null;
          user_defined_id: string;
      }

      LibraryListingV1

      A library listing.

      • closed_source: boolean

        Closed Source

        Whether the listing is closed source (deployers cannot view or download the Truss, and forks copy mirrored weights instead of re-mirroring from upstream)

      • created_at: string

        Created At Format: date-time

        Time the listing was created in ISO 8601 format

      • display_name: string

        Display Name

        Display name of the library listing

      • is_public: boolean

        Is Public

        Whether the listing is publicly accessible

      • metadata: components["schemas"]["LibraryListingMetadata"] | null

        Model-level metadata for this listing, if it has been uploaded.

        null
        
      • modified_at: string

        Modified At Format: date-time

        Time the listing was last modified

      • trending: boolean | null

        Trending

        Whether the listing is trending

      • user_defined_id: string

        User Defined Id

        User-defined identifier of the library listing

    • LibraryListingMetadata: {
          context_length?: number | null;
          description?: string | null;
          input_modalities?: components["schemas"]["LibraryListingModality"][];
          license: string;
          model_api_slug?: string | null;
          output_modalities?: components["schemas"]["LibraryListingModality"][];
          parameter_count?: number | null;
          publisher?: string | null;
          release_date?: string | null;
          trending?: boolean;
          variant?: string | null;
      }

      LibraryListingMetadataV1

      • Optionalcontext_length?: number | null

        Context Length

      • Optionaldescription?: string | null

        Description

      • Optionalinput_modalities?: components["schemas"]["LibraryListingModality"][]

        Input Modalities

      • license: string

        License

      • Optionalmodel_api_slug?: string | null

        Model Api Slug

      • Optionaloutput_modalities?: components["schemas"]["LibraryListingModality"][]

        Output Modalities

      • Optionalparameter_count?: number | null

        Parameter Count

      • Optionalpublisher?: string | null

        Publisher

      • Optionalrelease_date?: string | null

        Release Date

      • Optionaltrending?: boolean

        Trending

      • Optionalvariant?: string | null

        Variant

    • LibraryListingModality: "text" | "image" | "audio" | "video" | "embedding" | "rerank"

      LibraryListingModality

    • LibraryListings: { listings: components["schemas"]["LibraryListing"][] }

      LibraryListingsV1

      A list of library listings.

    • LibraryListingSource: {
          deployed_model_name?: string | null;
          kind: "library_listing";
          lab_display_name: string;
          user_defined_listing_id: string;
      }

      LibraryListingSourceV1

      Create a model by forking a library listing accessible to the caller's organization.

      • Optionaldeployed_model_name?: string | null

        Deployed Model Name

        Optional name for the new deployed model. Defaults to the listing's configured name.

      • kind: "library_listing"

        discriminator enum property added by openapi-typescript

      • lab_display_name: string

        Lab Display Name

        Identifier of the publishing organization, as returned by GET /v1/library_models.

      • user_defined_listing_id: string

        User Defined Listing Id

        Listing identifier within the publishing organization.

    • LibraryListingTombstone: { deleted: boolean; user_defined_id: string }

      LibraryListingTombstoneV1

      A library listing tombstone.

      • deleted: boolean

        Deleted

        Whether the library listing was deleted

      • user_defined_id: string

        User Defined Id

        User-defined identifier of the library listing

    • LibraryListingVersion: {
          allow_truss_download: boolean;
          benchmark: components["schemas"]["BenchmarkSnapshot"] | null;
          created_at: string;
          is_live: boolean;
          modified_at: string;
          oracle_version_id: string;
          version_tag: string;
      }

      LibraryListingVersionV1

      A library listing version.

      • allow_truss_download: boolean

        Allow Truss Download

        Whether users deploying this model can download the Truss

      • benchmark: components["schemas"]["BenchmarkSnapshot"] | null

        Benchmark snapshot for this version, if one has been uploaded.

        null
        
      • created_at: string

        Created At Format: date-time

        Time the version was created in ISO 8601 format

      • is_live: boolean

        Is Live

        Whether this version is the live version

      • modified_at: string

        Modified At Format: date-time

        Time the version was last modified

      • oracle_version_id: string

        Oracle Version Id

        Id of the source model version

      • version_tag: string

        Version Tag

        Human-readable tag for this version

    • LibraryListingVersions: { versions: components["schemas"]["LibraryListingVersion"][] }

      LibraryListingVersionsV1

      A list of library listing versions.

    • LibraryListingVersionTombstone: { deleted: boolean; version_tag: string }

      LibraryListingVersionTombstoneV1

      A library listing version tombstone.

      • deleted: boolean

        Deleted

        Whether the library listing version was deleted

      • version_tag: string

        Version Tag

        Human-readable tag for this version

    • LimitEnforcement: "CASCADING" | "INDEPENDENT"

      LimitEnforcementV1

    • LimitType:
          | "REQUEST"
          | "TOKEN"
          | "CONCURRENT_REQUEST"
          | "UNCACHED_INPUT_TOKEN"
          | "OUTPUT_TOKEN"

      LimitTypeV1

    • ListAuditLogsResponse: {
          items: components["schemas"]["AuditLogEntry"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      ListAuditLogsResponseV1

      A page of audit-log entries, newest first by default.

    • ListLoopsCheckpointsResponse: { checkpoints: components["schemas"]["LoopsCheckpoint"][] }

      ListLoopsCheckpointsResponseV1

      Checkpoints matching the query filter.

      • checkpoints: components["schemas"]["LoopsCheckpoint"][]

        Checkpoints

        Matching checkpoints.

    • ListLoopsDeploymentsResponse: { deployments: components["schemas"]["LoopsDeployment"][] }

      ListLoopsDeploymentsResponseV1

      Response for GET /v1/loops/deployments.

      Defaults to the caller's own; pass ``?scope=org`` to list every deployment in
      the caller's organization. Returns every deployment regardless of status;
      clients filter terminal states.
      
      • deployments: components["schemas"]["LoopsDeployment"][]

        Deployments

        Active Loops deployments.

    • ListLoopsRunsResponse: { runs: components["schemas"]["LoopsRun"][] }

      ListLoopsRunsResponseV1

      Runs matching the query filters.

    • ListLoopsSamplersResponse: { samplers: components["schemas"]["LoopsSampler"][] }

      ListLoopsSamplersResponseV1

      Response for GET /v1/loops/samplers.

      Returns the caller's samplers, including those paired to runs and
      standalone samplers. Ordered newest-first.
      
    • ListTrainingJobsResponse: {
          training_jobs: components["schemas"]["TrainingJob"][];
          training_project: components["schemas"]["TrainingProject"];
      }

      ListTrainingJobsResponseV1

      A response to list training jobs.

      • training_jobs: components["schemas"]["TrainingJob"][]

        Training Jobs

        List of training jobs.

      • training_project: components["schemas"]["TrainingProject"]

        The training project.

    • ListTrainingProjectsResponse: { training_projects: components["schemas"]["TrainingProject"][] }

      ListTrainingProjectsResponseV1

      A response to list training projects.

      • training_projects: components["schemas"]["TrainingProject"][]

        Training Projects

        List of training projects.

    • ListVolumeNamespacesResponse: { items: string[]; pagination: components["schemas"]["PaginationResponse"] }

      ListVolumeNamespacesResponseV1

      A page of namespaces the caller can read.

      • items: string[]

        Items

        Items in this page.

      • pagination: components["schemas"]["PaginationResponse"]

        Pagination metadata for the page.

    • ListVolumesResponse: {
          items: components["schemas"]["Volume"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      ListVolumesResponseV1

      A page of volumes in one namespace.

    • ListVolumeVersionsResponse: { versions: components["schemas"]["VolumeVersion"][]; volume_sequence: number }

      ListVolumeVersionsResponseV1

      Every version of a volume, newest first.

      Unpaginated: `limit` and `cursor` are absent rather than accepted and
      ignored, so adding them once the volume service pages this listing is a
      purely additive change.
      
      • versions: components["schemas"]["VolumeVersion"][]

        Versions

        Versions of the volume, newest first.

      • volume_sequence: number

        Volume Sequence

        Revision of the volume as a whole when the versions were read. Pass it as expected_sequence on a later delete to make that delete conditional on the volume not having changed since. Distinct from the per-version sequence, which is the revision a version was committed at.

    • LLMBenchmarkMetrics: {
          cost_per_1m_tokens_usd?: number | null;
          max_concurrent_users_at_50ms_tpot?: number | null;
          output_tokens_per_sec_per_user_p50?: number | null;
          requests_per_sec_p50?: number | null;
          ttft_ms_p50?: number | null;
      }

      LLMBenchmarkMetricsV1

      • Optionalcost_per_1m_tokens_usd?: number | null

        Cost Per 1M Tokens Usd

      • Optionalmax_concurrent_users_at_50ms_tpot?: number | null

        Max Concurrent Users At 50Ms Tpot

      • Optionaloutput_tokens_per_sec_per_user_p50?: number | null

        Output Tokens Per Sec Per User P50

      • Optionalrequests_per_sec_p50?: number | null

        Requests Per Sec P50

      • Optionalttft_ms_p50?: number | null

        Ttft Ms P50

    • LLMModelHandle: {
          hostname: string;
          instance_type_name: string | null;
          model_id: string;
          version_id: string;
      }

      LLMModelHandleV1

      Handle for a BIS-LLM model deployment.

      • hostname: string

        Hostname

        Hostname used to invoke the model

      • instance_type_name: string | null

        Instance Type Name

        Name of the instance type the model deployment is running on

        null
        
      • model_id: string

        Model Id

        Unique identifier of the model

      • version_id: string

        Version Id

        Unique identifier of the model version

    • LoadCheckpointConfig: {
          checkpoints?: (
              | components["schemas"]["BasetenLatestCheckpointConfig"]
              | components["schemas"]["BasetenNamedCheckpointConfig"]
              | components["schemas"]["LoopsCheckpointConfig"]
          )[];
          download_folder?: string;
          enabled?: boolean;
      }

      LoadCheckpointConfig

      • Optionalcheckpoints?: (
            | components["schemas"]["BasetenLatestCheckpointConfig"]
            | components["schemas"]["BasetenNamedCheckpointConfig"]
            | components["schemas"]["LoopsCheckpointConfig"]
        )[]

        Checkpoints

        List of checkpoint configurations

      • Optionaldownload_folder?: string

        Download Folder

        Folder where checkpoints will be downloaded

      • Optionalenabled?: boolean

        Enabled

        Whether checkpoint loading is enabled

    • Log: {
          level: components["schemas"]["LogLevel"] | null;
          message: string;
          replica: string | null;
          request_id: string | null;
          timestamp: string;
      }

      LogV1

      • level: components["schemas"]["LogLevel"] | null

        Severity of the log line, if one was detected. null when unknown.

        null
        
      • message: string

        Message

        The contents of the log message. When the logger captured an exception, the traceback is appended after the message.

      • replica: string | null

        Replica

        The replica the log line was emitted from.

      • request_id: string | null

        Request Id

        The request ID associated with an inference request.

        null
        
      • timestamp: string

        Timestamp

        Epoch nanosecond timestamp of the log message.

    • LogLevel: "DEBUG" | "INFO" | "WARNING" | "ERROR"

      LogLevelV1

      A log severity level.

    • LoopsCheckpoint: {
          base_model: string | null;
          checkpoint_id: string;
          checkpoint_type: string;
          created_at: string;
          id: string;
          lora_adapter_config: { [key: string]: unknown } | null;
          run_id: string;
          size_bytes: number;
          sync_status: string | null;
          target: components["schemas"]["TrainerCheckpointTarget"];
      }

      LoopsCheckpointV1

      A checkpoint saved by a Loops run.

      • base_model: string | null

        Base Model

        The base model of the checkpoint.

      • checkpoint_id: string

        Checkpoint Id

        The ID of the checkpoint.

      • checkpoint_type: string

        Checkpoint Type

        The type of checkpoint.

      • created_at: string

        Created At Format: date-time

        The timestamp of the checkpoint in ISO 8601 format.

      • id: string

        Id

        The checkpoint ID.

      • lora_adapter_config: { [key: string]: unknown } | null

        Lora Adapter Config

        The adapter config of the checkpoint.

      • run_id: string

        Run Id

        The ID of the run that produced the checkpoint.

      • size_bytes: number

        Size Bytes

        The size of the checkpoint in bytes.

      • sync_status: string | null

        Sync Status

        Sync state of the checkpoint: SYNCING or COMPLETE.

        null
        
      • target: components["schemas"]["TrainerCheckpointTarget"]

        Whether this checkpoint is loadable by the sampler or by the run.

    • LoopsCheckpointConfig: {
          checkpoint_name: string;
          run_id: string;
          target?: "trainer" | "sampler";
          typ: "loops_checkpoint";
      }

      LoopsCheckpointConfig

      • checkpoint_name: string

        Checkpoint Name

        Name of the checkpoint to load

      • run_id: string

        Run Id

        ID of the Loops run to load the checkpoint from

      • Optionaltarget?: "trainer" | "sampler"

        Target

        Which checkpoint target to load: 'trainer' (full training state) or 'sampler' (inference weights)

      • typ: "loops_checkpoint"

        discriminator enum property added by openapi-typescript

    • LoopsCheckpointFilesResponse: {
          next_page_token: number | null;
          presigned_urls: components["schemas"]["CheckpointFile"][];
          total_count: number;
      }

      LoopsCheckpointFilesResponseV1

      Response with presigned URLs for files under a Loops checkpoint.

      • next_page_token: number | null

        Next Page Token

        Token to use for fetching the next page of results. None when there are no more results.

        null
        
      • presigned_urls: components["schemas"]["CheckpointFile"][]

        Presigned Urls

        List of presigned URLs for checkpoint files.

      • total_count: number

        Total Count

        Total number of checkpoint files available.

    • LoopsDebugArchiveFilesResponse: {
          next_page_token: string | null;
          presigned_urls: components["schemas"]["CheckpointFile"][];
      }

      LoopsDebugArchiveFilesResponseV1

      Response with presigned URLs for a Loops deployment's debug archive.

      • next_page_token: string | null

        Next Page Token

        null
        
      • presigned_urls: components["schemas"]["CheckpointFile"][]

        Presigned Urls

    • LoopsDeployment: {
          active_run_id: string | null;
          availability_model: components["schemas"]["V1AvailabilityModel"];
          base_model: string;
          base_url: string;
          created_at: string;
          id: string;
          instance_type: components["schemas"]["InstanceType"];
          latest_run_id: string | null;
          node_count: number;
          sampler: components["schemas"]["LoopsSampler"] | null;
          status: components["schemas"]["LoopsDeploymentStatus"];
          user: components["schemas"]["User"];
      }

      LoopsDeploymentV1

      A Loops deployment — the long-lived run + sampler pair owned by a user.

      The deployment's current sampler is included inline. The full list of
      samplers visible to the caller (across all deployments) lives at
      ``GET /v1/loops/samplers``.
      
      • active_run_id: string | null

        Active Run Id

        The ID of the run currently active on this deployment, if any. Null when the deployment's runs have been marked inactive (e.g. scale-to-zero) without a successor.

        null
        
      • availability_model: components["schemas"]["V1AvailabilityModel"]

        Capacity the trainer was scheduled on.

        dedicated
        
      • base_model: string

        Base Model

        The HuggingFace base model the deployment is fine-tuning.

      • base_url: string

        Base Url

        The run's base URL.

      • created_at: string

        Created At Format: date-time

        Time the deployment was created in ISO 8601 format.

      • id: string

        Id

        The Loops deployment ID.

      • instance_type: components["schemas"]["InstanceType"]

        Instance type backing the trainer.

      • latest_run_id: string | null

        Latest Run Id

        The ID of the most recent run on this deployment, active or not, so idle deployments still expose a usable run handle. Null only if the deployment has no runs.

        null
        
      • node_count: number

        Node Count

        Number of nodes backing the trainer.

        1
        
      • sampler: components["schemas"]["LoopsSampler"] | null

        The sampler bound to this deployment.

        null
        
      • status: components["schemas"]["LoopsDeploymentStatus"]

        Latest deployment status.

      • user: components["schemas"]["User"]

        The user who owns the Loops deployment.

    • LoopsDeploymentMetrics: {
          concurrent_requests: components["schemas"]["TrainingJobMetric"][];
          cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
          cpu_usage: components["schemas"]["TrainingJobMetric"][];
          ephemeral_storage: components["schemas"]["StorageMetrics"];
          gpu_memory_usage_bytes: {
              [key: string]: { timestamp: string; value: number }[];
          };
          gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
          inference_volume: components["schemas"]["TrainingJobMetric"][];
          inference_volume_by_status: components["schemas"]["InferenceVolumeByStatusDatapoint"][];
          per_node_metrics: components["schemas"]["LoopsDeploymentNodeMetrics"][];
          response_time_stats: components["schemas"]["ResponseTimeDatapoint"][];
      }

      LoopsDeploymentMetricsV1

      Metrics for a trainer (Loops) deployment.

      Service-level fields summarize HTTP traffic into the trainer pods (the
      Knative queue-proxy is the source). Compute fields are the leader-pod
      aggregate; ``per_node_metrics`` carries the full multinode breakdown.
      
      • concurrent_requests: components["schemas"]["TrainingJobMetric"][]

        Concurrent Requests

        Number of in-progress concurrent inference requests. Source: the queue-proxy revision_queue_depth gauge on http-usermetric.

      • cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][]

        Cpu Memory Usage Bytes

        Leader-pod CPU memory usage bytes.

      • cpu_usage: components["schemas"]["TrainingJobMetric"][]

        Cpu Usage

        Leader-pod CPU usage in cores.

      • ephemeral_storage: components["schemas"]["StorageMetrics"]

        Leader-pod ephemeral storage usage.

      • gpu_memory_usage_bytes: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Memory Usage Bytes

        Leader-pod GPU memory bytes per GPU rank.

      • gpu_utilization: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Utilization

        Leader-pod fractional GPU utilization per GPU rank.

      • inference_volume: components["schemas"]["TrainingJobMetric"][]

        Inference Volume

        Number of inference requests per unit time (requests per second).

      • inference_volume_by_status: components["schemas"]["InferenceVolumeByStatusDatapoint"][]

        Inference Volume By Status

        Request rate split by response code class.

      • per_node_metrics: components["schemas"]["LoopsDeploymentNodeMetrics"][]

        Per Node Metrics

        Per-node compute breakdown for multinode trainer deployments.

      • response_time_stats: components["schemas"]["ResponseTimeDatapoint"][]

        Response Time Stats

        Percentiles of the response time distribution.

    • LoopsDeploymentNodeMetrics: {
          cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
          cpu_usage: components["schemas"]["TrainingJobMetric"][];
          ephemeral_storage: components["schemas"]["StorageMetrics"];
          gpu_memory_usage_bytes: {
              [key: string]: { timestamp: string; value: number }[];
          };
          gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
          node_id: string;
      }

      LoopsDeploymentNodeMetricsV1

      Per-node compute metrics for a multinode trainer deployment.

      • cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][]

        Cpu Memory Usage Bytes

        CPU memory usage bytes.

      • cpu_usage: components["schemas"]["TrainingJobMetric"][]

        Cpu Usage

        CPU usage in cores.

      • ephemeral_storage: components["schemas"]["StorageMetrics"]

        Ephemeral storage usage.

      • gpu_memory_usage_bytes: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Memory Usage Bytes

        GPU memory usage bytes per GPU rank.

      • gpu_utilization: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Utilization

        Fractional GPU utilization per GPU rank.

      • node_id: string

        Node Id

        Identifier for the node.

    • LoopsDeploymentStatus: { name: components["schemas"]["Name"] }

      LoopsDeploymentStatusV1

      Latest deployment status for a Loops deployment.

    • LoopsRun: {
          base_model: string;
          base_url: string;
          created_at: string;
          deployment_id: string | null;
          id: string;
          name: string;
          sampler: components["schemas"]["LoopsSampler"] | null;
          session_id: string;
          status: components["schemas"]["LoopsRunStatus"];
          user: components["schemas"]["User"];
      }

      LoopsRunV1

      • base_model: string

        Base Model

        The HuggingFace base model the run is fine-tuning.

      • base_url: string

        Base Url

        The run's base URL.

      • created_at: string

        Created At Format: date-time

        Time the run was created in ISO 8601 format

      • deployment_id: string | null

        Deployment Id

        The ID of the Loops deployment the run executes on, if it has one.

        null
        
      • id: string

        Id

        The run ID.

      • name: string

        Name

        The run's display name.

      • sampler: components["schemas"]["LoopsSampler"] | null

        The sampler bound to this run, or null for a trainer-only run that has not yet created a sampler.

        null
        
      • session_id: string

        Session Id

        The session ID this run belongs to.

      • status: components["schemas"]["LoopsRunStatus"]

        The run's current status.

      • user: components["schemas"]["User"]

        The user who owns the run.

    • LoopsRunStatus: { name: components["schemas"]["LoopsRunStatusName"] }

      LoopsRunStatusV1

      The current status of a Loops run.

      • name: components["schemas"]["LoopsRunStatusName"]

        ACTIVE while the run is live; INACTIVE once replaced by a newer run or shut down.

    • LoopsRunStatusName: "ACTIVE" | "INACTIVE"

      LoopsRunStatusNameV1

      A Loops run's lifecycle state: ACTIVE or INACTIVE.

    • LoopsSampler: {
          base_model: string;
          base_url: string;
          created_at: string;
          deployment_id: string;
          id: string;
          instance_type: components["schemas"]["InstanceType"] | null;
          model_id: string;
          node_count: number;
          status: components["schemas"]["LoopsSamplerStatus"];
          user: components["schemas"]["User"];
      }

      LoopsSamplerV1

      • base_model: string

        Base Model

        The HuggingFace base model the sampler is serving.

      • base_url: string

        Base Url

      • created_at: string

        Created At Format: date-time

        Time the sampler was created in ISO 8601 format

      • deployment_id: string

        Deployment Id

        Hashid of the specific model deployment (version).

      • id: string

        Id

      • instance_type: components["schemas"]["InstanceType"] | null

        Instance type serving the sampler.

        null
        
      • model_id: string

        Model Id

        Hashid of the underlying Baseten model.

      • node_count: number

        Node Count

        Number of nodes serving the sampler.

        1
        
      • status: components["schemas"]["LoopsSamplerStatus"]

        The sampler's current status.

      • user: components["schemas"]["User"]

        The user who owns the sampler.

    • LoopsSamplerStatus: { name: components["schemas"]["DeploymentStatus"] }

      LoopsSamplerStatusV1

      The current status of a Loops sampler.

      • name: components["schemas"]["DeploymentStatus"]

        The current status of the Loops sampler.

    • LoopsSession: { id: string }

      LoopsSessionV1

      • id: string

        Id

    • LoopsUserConfig: {
          sampler_accelerator_priority: string[] | null;
          trainer_accelerator_priority: string[] | null;
      }

      LoopsUserConfigV1

      The caller's Loops user-level config (accelerator priorities).

      • sampler_accelerator_priority: string[] | null

        Sampler Accelerator Priority

        Ordered allowlist of GPU types for your Loops sampler deployments, highest priority first. Intersected with the org-level allowlist (org acts as a ceiling). Null means 'inherit the org-level allowlist'.

        [
        "H100",
        "H200"
        ]
      • trainer_accelerator_priority: string[] | null

        Trainer Accelerator Priority

        Ordered allowlist of GPU types for your Loops trainer deployments, highest priority first. Intersected with the org-level allowlist (org acts as a ceiling). Null means 'inherit the org-level allowlist'.

        [
        "H100",
        "H200"
        ]
    • Model: {
          created_at: string;
          deployments_count: number;
          development_deployment_id: string | null;
          id: string;
          instance_type_name: string;
          name: string;
          production_deployment_id: string | null;
          team_name: string;
      }

      ModelV1

      A model.

      • created_at: string

        Created At Format: date-time

        Time the model was created in ISO 8601 format

      • deployments_count: number

        Deployments Count

        Number of deployments of the model

      • development_deployment_id: string | null

        Development Deployment Id

        Unique identifier of the development deployment of the model

      • id: string

        Id

        Unique identifier of the model

      • instance_type_name: string

        Instance Type Name

        Name of the instance type for the production deployment of the model

      • name: string

        Name

        Name of the model

      • production_deployment_id: string | null

        Production Deployment Id

        Unique identifier of the production deployment of the model

      • team_name: string

        Team Name

        Name of the team associated with the model.

    • ModelAPI: {
          context_length: number;
          cost_per_million_input_tokens: number | string | null;
          cost_per_million_output_tokens: number | string | null;
          description: string;
          display_name: string;
          invoke_url: string;
          model_family: string | null;
          name: string;
          org_details: components["schemas"]["ModelAPIOrgDetails"] | null;
          rate_limits: components["schemas"]["RateLimit"][];
          release_date: string;
      }

      ModelAPIV1

      A Model API catalog row, optionally enriched with workspace-specific state.

      • context_length: number

        Context Length

        The model's context window length, in tokens.

        8192
        
      • cost_per_million_input_tokens: number | string | null

        Cost Per Million Input Tokens

        Effective cost per million input tokens, in dollars. Null when pricing is unavailable.

        0.13
        
      • cost_per_million_output_tokens: number | string | null

        Cost Per Million Output Tokens

        Effective cost per million output tokens, in dollars. Null when pricing is unavailable.

        0.50
        
      • description: string

        Description

        Description of the Model API.

      • display_name: string

        Display Name

        Human-readable name of the Model API.

        Llama 3.3 70B Instruct
        
      • invoke_url: string

        Invoke Url

        Base URL for invoking the Model API. OpenAI-shaped routes (e.g. /v1/chat/completions) live underneath this host.

        https://inference.baseten.co
        
      • model_family: string | null

        Model Family

        Family the underlying model belongs to.

        null
        
        META
        
        DEEPSEEK
        
        QWEN
        
      • name: string

        Name

        Identifier of the Model API. Stable, URL-safe slug used as the public identifier.

        llama-3-3-70b-instruct
        
      • org_details: components["schemas"]["ModelAPIOrgDetails"] | null

        Workspace-specific state. Null when the workspace has not added this Model API.

        null
        
      • rate_limits: components["schemas"]["RateLimit"][]

        Rate Limits

        Rate limits in effect for the workspace. Workspace-specific overrides are returned when the workspace has added this Model API and configured them; otherwise the catalog default rate limits are returned.

      • release_date: string

        Release Date Format: date

        Date the Model API was made available.

    • ModelApiCostDimension: "api_key_prefix" | "user" | "model" | "service_tier"

      ModelApiCostDimensionV1

    • ModelApiItem: {
          cached_input_tokens: number;
          daily?: components["schemas"]["DailyModelApiUsage"][];
          input_tokens: number;
          model_family: string | null;
          model_name: string;
          output_tokens: number;
          subtotal: number | string;
      }

      ModelApiItemV1

      • cached_input_tokens: number

        Cached Input Tokens

        Total cached input tokens for this model

      • Optionaldaily?: components["schemas"]["DailyModelApiUsage"][]

        Daily

        Daily usage breakdown

      • input_tokens: number

        Input Tokens

        Total input tokens for this model

      • model_family: string | null

        Model Family

        Model family (e.g., llama, mistral)

        null
        
      • model_name: string

        Model Name

        Model name

      • output_tokens: number

        Output Tokens

        Total output tokens for this model

      • subtotal: number | string

        Subtotal

        Subtotal cost in dollars for this model

    • ModelAPIOrgDetails: { added_at: string; last_used_at: string | null }

      ModelAPIOrgDetailsV1

      Workspace-specific state for a Model API.

      • added_at: string

        Added At Format: date-time

        When the workspace first added this Model API.

      • last_used_at: string | null

        Last Used At

        When the workspace last invoked this Model API. Null if the workspace has never invoked it.

        null
        
    • ModelApisCostBucket: { date: string; results?: components["schemas"]["ModelApisCostResult"][] }

      ModelApisCostBucketV1

      One daily bucket and the costs attributed to it.

      • date: string

        Date Format: date

        UTC calendar date for this bucket, from midnight inclusive to the next midnight exclusive.

      • Optionalresults?: components["schemas"]["ModelApisCostResult"][]

        Results

        Cost totals for the observed combinations of requested dimensions in this bucket, ordered by those dimensions. Empty when the day has no matching usage.

    • ModelApisCostResult: {
          api_key_prefixes: string[] | null;
          model: string | null;
          service_tier: string | null;
          subtotal: string;
          user_id: string | null;
      }

      ModelApisCostResultV1

      • api_key_prefixes: string[] | null

        Api Key Prefixes

        The single attributed API key prefix for this result. Null when not grouping by api_key_prefix or when attribution is unavailable.

        null
        
      • model: string | null

        Model

        Model identifier. Null when not grouping by model.

        null
        
      • service_tier: string | null

        Service Tier

        Service tier. Null when not grouping by service_tier or when attribution is unavailable.

        null
        
      • subtotal: string

        Subtotal

        Model API cost in USD for this day and grouping combination, returned as an exact decimal string preserving fractional-cent amounts. This amount may differ from finalized invoice amounts.

        0.00000123
        
      • user_id: string | null

        User Id

        Attributed user ID. Null when not grouping by user or when attribution is unavailable.

        null
        
    • ModelApisCostsResponse: {
          items: components["schemas"]["ModelApisCostBucket"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      ModelApisCostsResponseV1

      One non-overlapping bucket per UTC day, ordered oldest first with no gaps.

      Days without matching usage are included with an empty results list.
      
      • items: components["schemas"]["ModelApisCostBucket"][]

        Items

        Items in this page.

      • pagination: components["schemas"]["PaginationResponse"]

        Pagination metadata for the page.

    • ModelAPIsResponse: {
          items: components["schemas"]["ModelAPI"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      ModelAPIsResponseV1

      Page of Model APIs visible to the caller.

    • ModelApisUsage: {
          breakdown?: components["schemas"]["ModelApiItem"][];
          credits_used: number | string;
          subtotal: number | string;
          total: number | string;
      }

      ModelApisUsageV1

      • Optionalbreakdown?: components["schemas"]["ModelApiItem"][]

        Breakdown

        Per-model usage breakdown

      • credits_used: number | string

        Credits Used

        Credits applied in dollars

      • subtotal: number | string

        Subtotal

        Subtotal cost in dollars after applying credits used

      • total: number | string

        Total

        Total cost in dollars

    • ModelApisUsageBucket: {
          end_time: string;
          results?: components["schemas"]["ModelApisUsageResult"][];
          start_time: string;
      }

      ModelApisUsageBucketV1

      One time bucket and the usage recorded in it.

      • end_time: string

        End Time Format: date-time

        End of the bucket (exclusive), UTC

      • Optionalresults?: components["schemas"]["ModelApisUsageResult"][]

        Results

        Usage totals for this bucket, ordered by total tokens descending

      • start_time: string

        Start Time Format: date-time

        Start of the bucket (inclusive), UTC

    • ModelApisUsageResponse: {
          items: components["schemas"]["ModelApisUsageBucket"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      ModelApisUsageResponseV1

      A page of Model APIs token usage: contiguous time buckets, ordered oldest first.

      • items: components["schemas"]["ModelApisUsageBucket"][]

        Items

        Items in this page.

      • pagination: components["schemas"]["PaginationResponse"]

        Pagination metadata for the page.

    • ModelApisUsageResult: {
          api_key_prefix: string | null;
          cached_input_tokens: number;
          input_tokens: number;
          model: string | null;
          output_tokens: number;
          request_count: number;
          uncached_input_tokens: number;
          user_id: string | null;
      }

      ModelApisUsageResultV1

      Usage totals for one combination of the requested dimensions, within one bucket.

      • api_key_prefix: string | null

        Api Key Prefix

        Prefix of the API key the usage is attributed to. Null when not grouping by api_key or when the request was not authenticated with an API key.

        null
        
      • cached_input_tokens: number

        Cached Input Tokens

        Input tokens served from the prompt cache.

      • input_tokens: number

        Input Tokens

        Total input tokens, cached and uncached combined.

      • model: string | null

        Model

        Model that served the usage. Null when not grouping by model.

        null
        
      • output_tokens: number

        Output Tokens

        Total output tokens.

      • request_count: number

        Request Count

        Total number of requests.

      • uncached_input_tokens: number

        Uncached Input Tokens

        Input tokens not served from the prompt cache.

      • user_id: string | null

        User Id

        User the usage is attributed to. Null when not grouping by user or when the credential is not user-scoped.

        null
        
    • ModelArchiveSource: {
          deployment: components["schemas"]["DeploymentArchivePayload"];
          disable_archive_download?: boolean;
          kind: "model_archive";
          name: string;
          s3_key?: string | null;
      }

      ModelArchiveSourceV1

      Create a model from an archive previously uploaded via the credentials issued by POST /v1/prepare_model_upload.

      • deployment: components["schemas"]["DeploymentArchivePayload"]

        Deployment-level configuration for the model's first deployment.

      • Optionaldisable_archive_download?: boolean

        Disable Archive Download

        If true, the uploaded archive is not downloadable after creation. Locked at model creation; cannot be changed by subsequent deployments.

      • kind: "model_archive"

        discriminator enum property added by openapi-typescript

      • name: string

        Name

        Name of the new model.

      • Optionals3_key?: string | null

        S3 Key

        S3 key of the uploaded archive, from the credentials returned by POST /v1/prepare_model_upload. Omit for model formats that are not built from an archive (for example, BIS-LLM), where prepare issues no upload target.

    • ModelConfig: {
          rate_limits?: components["schemas"]["RateLimit"][];
          slug: string;
          usage_limits?: components["schemas"]["UsageLimit"][];
      }

      ModelConfigV1

      • Optionalrate_limits?: components["schemas"]["RateLimit"][]

        Rate Limits

      • slug: string

        Slug

        Shared endpoint slug.

      • Optionalusage_limits?: components["schemas"]["UsageLimit"][]

        Usage Limits

    • ModelMetricDescriptor: {
          kind: components["schemas"]["ModelMetricKind"];
          label_sets: { [key: string]: string }[];
          name: string;
          unit_hint: components["schemas"]["ModelMetricUnitHint"];
      }

      ModelMetricDescriptorV1

      Describes one metric. Its position in the response metric_descriptors list is the index used to read that metric out of each value set's values.

      A metric may break down into multiple labeled series (e.g. latency quantiles,
      or volume by status). ``label_sets`` enumerates those series in order; each
      value set's value for this metric is a list aligned to that order.
      
      • kind: components["schemas"]["ModelMetricKind"]

        Semantic hint for how the metric behaves (GAUGE, COUNTER, HISTOGRAM).

      • label_sets: { [key: string]: string }[]

        Label Sets

        The metric's series, in order. Each entry is the set of labels identifying one series; the value at the same index in each value set's values is that series' value. A plain metric has a single entry with no labels ({}). A histogram has one entry per quantile plus an average, e.g. {'quantile': '0.5'} … {'quantile': '0.99'}, {'stat': 'avg'}. A by-status metric has one entry per status, e.g. {'status': '2xx'}.

      • name: string

        Name

        Canonical metric name.

      • unit_hint: components["schemas"]["ModelMetricUnitHint"]

        Advisory unit of the metric's values.

    • ModelMetricKind: "GAUGE" | "COUNTER" | "HISTOGRAM"

      ModelMetricKindV1

      Semantic hint for how a metric behaves, to aid client rendering and aggregation. It does not describe the value's shape (that is carried by the descriptor's label_sets; a metric may break down into multiple series).

      - ``GAUGE``: an instantaneous value (e.g. queue size, running requests).
      - ``COUNTER``: a cumulative total over the step (e.g. tokens, restarts).
      - ``HISTOGRAM``: a distribution, exposed as quantile/average series.
      
    • ModelMetricMode: "CURRENT" | "SUMMARY" | "SERIES"

      ModelMetricModeV1

      How metric values are aggregated over the request.

    • ModelMetricUnitHint: "PER_SECOND" | "SECONDS" | "BYTES" | "MEBIBYTES" | "COUNT" | "RATIO"

      ModelMetricUnitHintV1

      Advisory unit of a metric's values. Values are reported as scraped, so the hint describes the raw value (e.g. GPU memory is reported in mebibytes).

      - ``PER_SECOND``: a rate per second.
      - ``SECONDS``: a duration in seconds.
      - ``BYTES``: a size in bytes.
      - ``MEBIBYTES``: a size in mebibytes (MiB).
      - ``COUNT``: a dimensionless tally of discrete things.
      - ``RATIO``: a dimensionless ratio. Usually in ``[0, 1]`` but may exceed 1
        (e.g. CPU usage in cores = cpu-seconds/second).
      
    • ModelMetricValueSet: { start_epoch_millis: number; values: (number | null)[][] }

      ModelMetricValueSetV1

      The metric values for one time step. values is aligned by index to the response metric_descriptors list.

      • start_epoch_millis: number

        Start Epoch Millis

        Start of the step. The step spans until the next value set's start, or the window end for the last one; a summary has a single value set starting at the window start.

      • values: (number | null)[][]

        Values

        Metric values aligned to the metric_descriptors index. Each entry is a list aligned to that descriptor's label_sets (a single-element list for a plain metric). A series with no data in this step is null.

    • Models: { models: components["schemas"]["Model"][] }

      ModelsV1

      A list of models.

    • ModelTombstone: { deleted: boolean; id: string }

      ModelTombstoneV1

      A model tombstone.

      • deleted: boolean

        Deleted

        Whether the model was deleted

      • id: string

        Id

        Unique identifier of the model

    • Name:
          | "CREATED"
          | "DEPLOYING"
          | "RUNNING"
          | "SCALED_TO_ZERO"
          | "FAILED"
          | "STOPPED"
          | "PREEMPTED"

      LoopsDeploymentStatus

    • OneTimeAutoscalingSchedule: {
          autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"];
          cadence: "ONE_TIME";
          enabled: boolean;
          end_at: string;
          id: string;
          name: string;
          start_at: string;
      }

      OneTimeAutoscalingScheduleV1

      • autoscaling_settings: components["schemas"]["AutoscalingScheduleSettings"]

        Raw autoscaling overrides applied during the schedule window

      • cadence: "ONE_TIME"

        One-time schedule cadence (enum property replaced by openapi-typescript)

      • enabled: boolean

        Enabled

        Whether the schedule is enabled

      • end_at: string

        End At Format: date-time

        Exclusive end of the schedule window

      • id: string

        Id

        Stable unique identifier of the schedule

      • name: string

        Name

        Name of the schedule

      • start_at: string

        Start At Format: date-time

        Inclusive start of the schedule window

    • OneTimeAutoscalingScheduleUpsert: {
          autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"];
          cadence: "ONE_TIME";
          enabled: boolean;
          end_at: string;
          id?: string | null;
          name: string;
          start_at: string;
      }

      OneTimeAutoscalingScheduleUpsertV1

      A complete one-time schedule submitted for create or replacement.

      • autoscaling_settings: components["schemas"]["AutoscalingScheduleSettingsRequest"]

        Complete raw autoscaling overrides for the schedule. Every field is required; nullable fields store no schedule override and follow the current environment value.

      • cadence: "ONE_TIME"

        One-time schedule cadence (enum property replaced by openapi-typescript)

      • enabled: boolean

        Enabled

        Whether the schedule is enabled

      • end_at: string

        End At Format: date-time

        Exclusive end of the schedule window in ISO 8601 format

      • Optionalid?: string | null

        Id

        Stable schedule identifier. Omit this field to create a schedule.

      • name: string

        Name

        Name of the schedule

      • start_at: string

        Start At Format: date-time

        Inclusive start of the schedule window in ISO 8601 format. New schedules must start in the future.

    • OrderBy: { field: string; order: string }

      OrderByV1

      A request to order training jobs.

      • field: string

        Field

        The field to order by.

        created_at
        
      • order: string

        Order

        The direction to order by.

        asc
        
        desc
        
    • OrganizationInfo: {
          aws_assume_role: components["schemas"]["AwsAssumeRole"] | null;
          created_at: string;
          name: string | null;
          org_id: string;
      }

      OrganizationInfoV1

      The caller's organization.

      • aws_assume_role: components["schemas"]["AwsAssumeRole"] | null

        AWS AssumeRole trust-policy inputs; null while the method is not enabled for the organization

        null
        
      • created_at: string

        Created At Format: date-time

        Time the organization was created in ISO 8601 format

      • name: string | null

        Name

        Display name of the organization

        null
        
      • org_id: string

        Org Id

        Unique identifier for the organization

    • PaginationResponse: { cursor: string | null; has_more: boolean }

      PaginationResponseV1

      • cursor: string | null

        Cursor

        Opaque cursor to pass into the next request. Null when there is no next page.

        null
        
      • has_more: boolean

        Has More

        Whether more items exist after this page.

    • PatchInteractiveSessionRequest: {
          timeout_minutes?: number | null;
          trigger?: components["schemas"]["V1InteractiveSessionTrigger"] | null;
      }

      PatchInteractiveSessionRequestV1

      Request to patch an interactive session.

      Only fields that are provided (non-None) will be applied.
      
      • Optionaltimeout_minutes?: number | null

        Timeout Minutes

        For on_startup sessions, minutes to add to the expiration. For on_demand/on_failure sessions, minutes to add to the timeout. Use -1 for infinite timeout (bumps by 10 years).

      • Optionaltrigger?: components["schemas"]["V1InteractiveSessionTrigger"] | null

        Update when the interactive session is created. Cannot be changed if the session trigger is 'on_startup'.

    • PatchInteractiveSessionResponse: {
          interactive_session: components["schemas"]["InteractiveSession"];
          message: string;
      }

      PatchInteractiveSessionResponseV1

      Response after patching an interactive session.

      • interactive_session: components["schemas"]["InteractiveSession"]

        The updated interactive session.

      • message: string

        Message

        Human-readable summary of what was updated.

    • PatchLoopsUserConfigRequest: {
          sampler_accelerator_priority?: string[] | null;
          trainer_accelerator_priority?: string[] | null;
      }

      PatchLoopsUserConfigRequestV1

      Request body for PATCH /v1/loops/user_config.

      Follows JSON Merge Patch (RFC 7396) semantics per field: omit the field
      to leave it unchanged, send ``null`` to clear and inherit the org-level
      allowlist, send a list to set the allowlist. Empty lists are rejected
      because the storage layer normalizes ``null`` and ``[]`` identically, so
      accepting both would create two ways to spell the same intent.
      
      • Optionalsampler_accelerator_priority?: string[] | null

        Sampler Accelerator Priority

        Ordered list of GPU types for sampler deployments, highest priority first. Send a list to set; send null to clear (inherit org allowlist); omit to leave unchanged. Empty list is rejected.

        [
        "H100",
        "H200"
        ]
      • Optionaltrainer_accelerator_priority?: string[] | null

        Trainer Accelerator Priority

        Ordered list of GPU types for trainer deployments, highest priority first. Send a list to set; send null to clear (inherit org allowlist); omit to leave unchanged. Empty list is rejected.

        [
        "H100",
        "H200"
        ]
    • PatchLoopsUserConfigResponse: { user_config: components["schemas"]["LoopsUserConfig"] }

      PatchLoopsUserConfigResponseV1

      Response for PATCH /v1/loops/user_config.

      • user_config: components["schemas"]["LoopsUserConfig"]

        The updated Loops user config.

    • PatchTeamTrainingGpuCapacityRequest: { gpu_type: string; max_gpus: number; team_id: string }

      PatchTeamTrainingGpuCapacityRequestV1

      A request to set the GPU capacity ceiling for a (team, gpu_type) pair.

      Creates the limit if one doesn't already exist for this team and GPU type,
      otherwise updates it in place.
      
      • gpu_type: string

        Gpu Type

        GPU type identifier (e.g. H100, A100-40GB)

      • max_gpus: number

        Max Gpus

        Max concurrent GPUs of this type the team may use

        8
        
        16
        
        32
        
      • team_id: string

        Team Id

        Team identifier

    • PatchTeamTrainingGpuCapacityResponse: { team_gpu_capacity: components["schemas"]["TeamTrainingGpuCapacityItem"] }

      PatchTeamTrainingGpuCapacityResponseV1

      Response for setting a team's GPU capacity ceiling.

      • team_gpu_capacity: components["schemas"]["TeamTrainingGpuCapacityItem"]

        The updated per-team GPU capacity limit

    • PendingJobAheadAtSubmit: {
          instance_type_name: string;
          priority: number;
          requested_gpus: number;
          submitted_at: string;
          training_job_id: string;
          training_job_name: string | null;
      }

      PendingJobAheadAtSubmitV1

      A PENDING job in the same (org, gpu_type) pool that was ahead of the target in dequeue FIFO order at submitted_at — higher priority, or same priority and earlier submission.

      • instance_type_name: string

        Instance Type Name

        Instance type of the other job

      • priority: number

        Priority

        Effective priority (NULL coalesced to 0)

      • requested_gpus: number

        Requested Gpus

        gpu_count * effective_node_count

      • submitted_at: string

        Submitted At Format: date-time

        The other job's submission time

      • training_job_id: string

        Training Job Id

        Hashid of the other training job

      • training_job_name: string | null

        Training Job Name

        Other job's name

        null
        
    • PrepareModelUploadRequest: {
          deployment: components["schemas"]["DeploymentArchivePayload"];
          dry_run?: boolean;
          model_id?: string | null;
          name?: string | null;
          team_id?: string | null;
      }

      PrepareModelUploadRequestV1

      Body for POST /v1/prepare_model_upload.

      Validates the same payload the commit endpoint will validate, and on
      `dry_run=false` issues STS upload credentials. Exactly one of `name` or
      `model_id` is required: `name` validates the new-model path (`POST
      /v1/models`); `model_id` validates the add-deployment path (`POST
      /v1/models/{model_id}/deployments`).
      
      • deployment: components["schemas"]["DeploymentArchivePayload"]

        Deployment-level payload, identical to the payload sent at commit.

      • Optionaldry_run?: boolean

        Dry Run

        If true, validate the payload only and do not issue upload credentials. The response sets creds, s3_bucket, and s3_key to null.

      • Optionalmodel_id?: string | null

        Model Id

        Set to validate an add-deployment push to an existing model. Exactly one of name or model_id is required.

      • Optionalname?: string | null

        Name

        Set to validate a new-model push. Exactly one of name or model_id is required.

      • Optionalteam_id?: string | null

        Team Id

        Team the new model will belong to. Only valid when name is set; defaults to the organization's default team when omitted. Must not be set when model_id is set (the existing model already has a team).

    • PrepareModelUploadResponse: {
          creds: components["schemas"]["AWSCredentials"] | null;
          s3_bucket: string | null;
          s3_key: string | null;
          s3_region: string | null;
      }

      PrepareModelUploadResponseV1

      Response from POST /v1/prepare_model_upload.

      Returns STS upload credentials when the push requires an archive upload. All
      four fields (`creds`, `s3_bucket`, `s3_key`, `s3_region`) are `null` when no
      upload is needed: either `dry_run=true` (validation only) or a model format
      that is not built from an uploaded archive (for example, BIS-LLM, which is
      built from its config alone).
      
      • creds: components["schemas"]["AWSCredentials"] | null

        STS credentials to upload the model archive. Null when no archive upload is required.

        null
        
      • s3_bucket: string | null

        S3 Bucket

        S3 bucket the credentials are scoped to. Null when no archive upload is required.

        null
        
      • s3_key: string | null

        S3 Key

        S3 key the credentials are scoped to. Pass this to POST /v1/models (in the model_archive source) once the upload completes. Null when no archive upload is required.

        null
        
      • s3_region: string | null

        S3 Region

        AWS region the S3 bucket resides in. Null when no archive upload is required.

        null
        
    • PromoteRequest: {
          preserve_env_instance_type?: boolean;
          scale_down_previous_production?: boolean;
      }

      PromoteRequestV1

      A request to promote a deployment to production.

      • Optionalpreserve_env_instance_type?: boolean

        Preserve Env Instance Type

        Whether to use the promoting deployment's instance type or preserve target environment's instance type

        true
        
      • Optionalscale_down_previous_production?: boolean

        Scale Down Previous Production

        Whether to scale down the previous production deployment after promoting

        true
        
    • PromoteToChainEnvironmentRequest: { deployment_id: string; scale_down_previous_deployment?: boolean }

      PromoteToChainEnvironmentRequestV1

      A request to promote a deployment to a environment.

      • deployment_id: string

        Deployment Id

        The id of the chain deployment to promote

      • Optionalscale_down_previous_deployment?: boolean

        Scale Down Previous Deployment

        Whether to scale down the previous deployment after promoting

        true
        
    • PromoteToEnvironmentRequest: {
          deployment_id: string;
          preserve_env_instance_type?: boolean;
          scale_down_previous_deployment?: boolean;
      }

      PromoteToEnvironmentRequestV1

      A request to promote a deployment to a environment.

      • deployment_id: string

        Deployment Id

        The id of the deployment to promote

      • Optionalpreserve_env_instance_type?: boolean

        Preserve Env Instance Type

        Whether to use the promoting deployment's instance type or preserve target environment's instance type

        true
        
      • Optionalscale_down_previous_deployment?: boolean

        Scale Down Previous Deployment

        Whether to scale down the previous deployment after promoting

        true
        
    • PromotionCleanupStrategy: "KEEP" | "SCALE_TO_ZERO" | "DEACTIVATE"

      PromotionCleanupStrategyV1

      The promotion cleanup strategy.

    • PromotionSettings: {
          promotion_cleanup_strategy:
              | components["schemas"]["PromotionCleanupStrategy"]
              | null;
          ramp_up_duration_seconds: number
          | null;
          ramp_up_while_promoting: boolean | null;
          redeploy_on_promotion: boolean | null;
          rolling_deploy: boolean | null;
          rolling_deploy_config: components["schemas"]["RollingDeployConfig"] | null;
      }

      PromotionSettingsV1

      Promotion settings for promoting chains and oracles

      • promotion_cleanup_strategy: components["schemas"]["PromotionCleanupStrategy"] | null

        The cleanup strategy to use after a promotion completes.

        SCALE_TO_ZERO
        
        SCALE_TO_ZERO
        
      • ramp_up_duration_seconds: number | null

        Ramp Up Duration Seconds

        Duration of the ramp up in seconds

        600
        
        600
        
      • ramp_up_while_promoting: boolean | null

        Ramp Up While Promoting

        Whether to ramp up traffic while promoting

        false
        
        true
        
      • redeploy_on_promotion: boolean | null

        Redeploy On Promotion

        Whether to deploy on all promotions. Enabling this flag allows model code to safely handle environment-specific logic. When a deployment is promoted, a new deployment will be created with a copy of the image.

        false
        
        true
        
      • rolling_deploy: boolean | null

        Rolling Deploy

        Whether the environment should rely on rolling deploy orchestration.

        false
        
        true
        
      • rolling_deploy_config: components["schemas"]["RollingDeployConfig"] | null

        Rolling deploy configuration for promotions

        null
        
    • QueueEvent: {
          created: string;
          event_message: string | null;
          exit_code: number | null;
          status: string;
          training_job_id: string;
          training_job_name: string | null;
      }

      QueueEventV1

      A single TrainingJobStatus row inside the queue-context window.

      • created: string

        Created Format: date-time

        When the status row was inserted

      • event_message: string | null

        Event Message

        Human-readable event message from the status metadata

        null
        
      • exit_code: number | null

        Exit Code

        Exit code from the status metadata, if any

        null
        
      • status: string

        Status

        TrainingJobStatus.Name value

      • training_job_id: string

        Training Job Id

        Hashid of the training job this event is for

      • training_job_name: string | null

        Training Job Name

        Job name

        null
        
    • RateLimit: {
          threshold: number;
          type: components["schemas"]["LimitType"];
          unit: components["schemas"]["RateLimitUnit"];
      }

      RateLimitV1

      • threshold: number

        Threshold

        The threshold for the rate limit

        1000
        
        50000
        
      • type: components["schemas"]["LimitType"]

        The type of the rate limit

        TOKEN
        
        REQUEST
        
      • unit: components["schemas"]["RateLimitUnit"]

        The unit of the rate limit

        SECOND
        
        MINUTE
        
    • RateLimitUnit: "SECOND" | "MINUTE"

      RateLimitUnitV1

    • RecreateTrainingJobResponse: { training_job: components["schemas"]["TrainingJob"] }

      RecreateTrainingJobResponseV1

      A response that sends the new training job

    • Region: { display_name: string; slug: string }

      RegionV1

      A region that deployments can be placed in.

      • display_name: string

        Display Name

        Human-readable name of the region.

        United States
        
      • slug: string

        Slug

        Stable identifier for the region, used when selecting a deployment region.

        us
        
    • Regions: { regions: components["schemas"]["Region"][] }

      RegionsV1

      A list of regions.

    • RegisterAPIKeyRequest: { key: string; name?: string | null }

      RegisterAPIKeyRequestV1

      Request to register a caller-supplied API key against an existing FederatedGroup.

      • key: string

        Key

        Value of the API key to register

        my-secure-api-key-value
        
      • Optionalname?: string | null

        Name

        Optional name for the Model API key

        my-model-api-key
        
    • RegisterAPIKeyResponse: { ok: boolean }

      RegisterAPIKeyResponseV1

      • ok: boolean

        Ok

        Whether the registration was successful

    • RegistrySecretDockerAuth: { secret_ref: components["schemas"]["SecretReference"] }

      RegistrySecretDockerAuthV1

      Authentication via a Baseten secret for any Docker registry (Docker Hub, GHCR, NGC, etc.). The referenced secret must contain credentials in the format 'username:password'. For Docker Hub, set registry to 'https://index.docker.io/v1/'. For GHCR, use 'ghcr.io'.

      • secret_ref: components["schemas"]["SecretReference"]

        Reference to a Baseten secret containing credentials in the format 'username:password'

    • RequestBackpressurePolicy: "QUEUE_ON_FULL" | "REJECT_ON_FULL"

      RequestBackpressurePolicyV1

    • RequestBackpressureSettings: { policy: components["schemas"]["RequestBackpressurePolicy"] | null }

      RequestBackpressureSettingsV1

      Request backpressure settings for a deployment or environment.

      • policy: components["schemas"]["RequestBackpressurePolicy"] | null

        Backpressure policy. Null when no policy is set.

        null
        
    • ResourceKind:
          | "LOOPS_SAMPLER"
          | "LOOPS_TRAINER"
          | "MODEL_DEPLOYMENT"
          | "TRAINING_JOB"
          | "CHAINLET"

      ResourceKind

    • ResponseTimeDatapoint: {
          p50: number | null;
          p95: number | null;
          p99: number | null;
          timestamp: string;
      }

      ResponseTimeDatapointV1

      Latency quantile datapoint. Values are reported in milliseconds.

      • p50: number | null

        P50

        50th percentile request latency (milliseconds).

        null
        
      • p95: number | null

        P95

        95th percentile request latency (milliseconds).

        null
        
      • p99: number | null

        P99

        99th percentile request latency (milliseconds).

        null
        
      • timestamp: string

        Timestamp Format: date-time

        ISO 8601 timestamp.

    • RestoreVolumeVersionRequest: { expected_sequence?: number | null }

      RestoreVolumeVersionRequestV1

      • Optionalexpected_sequence?: number | null

        Expected Sequence

        Revision the volume is expected to be at. When set, the restore fails with a conflict if the volume has changed since. Take the value from volume_sequence.

    • RestoreVolumeVersionResponse: {
          digest: string;
          lifecycle: string;
          namespace: string;
          version_ref: string;
          volume: string;
          volume_sequence: number;
      }

      RestoreVolumeVersionResponseV1

      • digest: string

        Digest

        Content digest of the restored version, as b3:<hex>.

      • lifecycle: string

        Lifecycle

        Lifecycle state of the version after the restore.

      • namespace: string

        Namespace

        Namespace the volume belongs to, in lowercase.

      • version_ref: string

        Version Ref

        Full address of the restored version, as bdn:<namespace>/<volume>@<digest>.

      • volume: string

        Volume

        Name of the volume, in lowercase.

      • volume_sequence: number

        Volume Sequence

        Revision of the volume after the restore.

    • RetryDeploymentResponse: {
          deployment: components["schemas"]["Deployment"];
          reason: string | null;
          retried: boolean;
      }

      RetryDeploymentResponseV1

      The response to a request to retry a deployment.

      • deployment: components["schemas"]["Deployment"]

        The deployment that was retried

      • reason: string | null

        Reason

        Explanation of the result. Provided when retried is false to explain why retry was not possible.

        null
        
      • retried: boolean

        Retried

        Whether the retry was successfully initiated

    • RollingDeployConfig: {
          max_surge_percent: number;
          max_unavailable_percent: number;
          replica_overhead_percent: number;
          rolling_deploy_strategy: components["schemas"]["RollingDeployStrategy"];
          stabilization_time_seconds: number;
      }

      RollingDeployConfigV1

      Rolling deploy config for promoting chains and oracles

      • max_surge_percent: number

        Max Surge Percent

        The maximum surge percentage for rolling deploys.

        25
        
        25
        
      • max_unavailable_percent: number

        Max Unavailable Percent

        The maximum unavailable percentage for rolling deploys.

        0
        
        10
        
      • replica_overhead_percent: number

        Replica Overhead Percent

        The replica overhead percentage for rolling deploys.

        0
        
        0
        
      • rolling_deploy_strategy: components["schemas"]["RollingDeployStrategy"]

        The rolling deploy strategy to use for promotions.

        REPLICA
        
        REPLICA
        
      • stabilization_time_seconds: number

        Stabilization Time Seconds

        The stabilization time in seconds for rolling deploys.

        0
        
        300
        
    • RollingDeployStrategy: "REPLICA"

      RollingDeployStrategyV1

      The rolling deploy strategy.

    • SearchTrainingJobsRequest: {
          job_id?: string | null;
          order_by?: components["schemas"]["OrderBy"][];
          project_id?: string | null;
          statuses?: string[] | null;
      }

      SearchTrainingJobsRequestV1

      A request to search training jobs.

      • Optionaljob_id?: string | null

        Job Id

        Filter the training jobs by job ID.

        p7qr9qv
        
      • Optionalorder_by?: components["schemas"]["OrderBy"][]

        Order By

        Order the training jobs by a field. Currently supports created_at

      • Optionalproject_id?: string | null

        Project Id

        Filter the training jobs by project ID.

        n4q95w5
        
      • Optionalstatuses?: string[] | null

        Statuses

        Filter the training jobs by status.

        [
        "TRAINING_JOB_RUNNING",
        "TRAINING_JOB_COMPLETED"
        ]
    • SearchTrainingJobsResponse: { training_jobs: components["schemas"]["TrainingJob"][] }

      SearchTrainingJobsResponseV1

      A response to search training jobs.

      • training_jobs: components["schemas"]["TrainingJob"][]

        Training Jobs

        List of training jobs.

    • Secret: { created_at: string; id: string; name: string; team_name: string }

      SecretV1

      A Baseten secret. Note that we do not support retrieving secret values.

      • created_at: string

        Created At Format: date-time

        Time the secret was created in ISO 8601 format

      • id: string

        Id

        Stable identifier for the secret. Unchanged across rotation.

        3kZ9xqd
        
      • name: string

        Name

        Name of the secret

      • team_name: string

        Team Name

        Name of the team the secret belongs to

    • SecretReference: { name: string }

      SecretReferenceV1

      • name: string

        Name

        Name of the secret to reference.

        hf_token
        
    • Secrets: { secrets: components["schemas"]["Secret"][] }

      SecretsV1

      A list of Baseten secrets.

    • SecretTombstone: { name: string }

      SecretTombstoneV1

      A secret tombstone.

      • name: string

        Name

        Name of the deleted secret

    • SharedEndpointRegion: "UNRESTRICTED" | "EU"

      SharedEndpointRegionV1

    • SignalPromotionResponse: { success: boolean }

      SignalPromotionResponseV1

      The response to a request to signal a rolling promotion.

      • success: boolean

        Success

        Whether the signal was successfully sent

    • SignSSHCertificateRequest: { public_key: string; replica_id?: string | null }

      SignSSHCertificateRequestV1

      Request to sign an SSH certificate for accessing a workload pod.

      • public_key: string

        Public Key

        The user's SSH public key (e.g., 'ssh-ed25519 AAAA... user@host').

      • Optionalreplica_id?: string | null

        Replica Id

        The replica to connect to. Required for training jobs (e.g. '0'). Optional for inference (server picks a running replica if omitted).

    • SignSSHCertificateResponse: {
          jwt: string;
          proxy_address: string;
          ssh_cert_expires_at: string;
          ssh_certificate: string;
      }

      SignSSHCertificateResponseV1

      Response containing a signed SSH certificate for proxy authentication.

      • jwt: string

        Jwt

        Signed JWT (ES256) for SSH proxy authorization.

      • proxy_address: string

        Proxy Address

        Address of the SSH proxy to connect to (host:port).

      • ssh_cert_expires_at: string

        Ssh Cert Expires At Format: date-time

        When the certificate expires, in ISO 8601 format.

      • ssh_certificate: string

        Ssh Certificate

        The signed SSH certificate in OpenSSH format.

    • SortOrder: "asc" | "desc"

      SortOrderV1

    • StopTrainingJobRequest: Record<string, unknown>

      StopTrainingJobRequestV1

      A request to stop a training job.

    • StopTrainingJobResponse: { training_job: components["schemas"]["TrainingJob"] }

      StopTrainingJobResponseV1

      A response to stopping a training job.

    • StorageMetrics: {
          usage_bytes: components["schemas"]["TrainingJobMetric"][];
          utilization: components["schemas"]["TrainingJobMetric"][];
      }

      StorageMetricsV1

      A metric for a training job.

      • usage_bytes: components["schemas"]["TrainingJobMetric"][]

        Usage Bytes

        The number of bytes used on the storage entity.

      • utilization: components["schemas"]["TrainingJobMetric"][]

        Utilization

        The utilization of the storage entity as a decimal percentage.

    • SupportedModel: {
          max_context_length: number;
          model_name: string;
          supports_vision_language: boolean;
      }

      SupportedModelV1

      A model supported by the Loops server.

      • max_context_length: number

        Max Context Length

        The maximum context length (in tokens) supported by this model.

      • model_name: string

        Model Name

        The name of the supported model.

      • supports_vision_language: boolean

        Supports Vision Language

        Whether the model accepts image inputs alongside text.

    • SyncDeploymentPatchesRequest: Record<string, unknown>

      SyncDeploymentPatchesRequestV1

      Triggers a sync of any staged patches to the running deployment. Takes no fields: the deployment and its staged patches fully determine the sync.

    • SyncDeploymentPatchesResponse: { needs_full_deploy_reason: string | null }

      SyncDeploymentPatchesResponseV1

      The outcome of a sync that ran.

      Operational failures (a transient patch failure, an invalid patch sequence)
      are surfaced as HTTP errors rather than fields here, so a 2xx means the sync
      reached a verdict.
      
      • needs_full_deploy_reason: string | null

        Needs Full Deploy Reason

        If set, the change cannot be patched and a full push is required; the value explains why. If null, the deployment is now in sync.

        null
        
    • Team: { created_at: string; default: boolean; id: string; name: string }

      TeamV1

      A team.

      • created_at: string

        Created At Format: date-time

        Time the team was created in ISO 8601 format

      • default: boolean

        Default

        Whether this is the default team for the organization

      • id: string

        Id

        Unique identifier of the team

      • name: string

        Name

        Name of the team

    • Teams: { teams: components["schemas"]["Team"][] }

      TeamsV1

      A list of teams.

    • TeamTrainingGpuCapacityItem: {
          baseline: number;
          dedicated_usage_count: number;
          gpu_type: string;
          limit: number;
          spot_usage_count: number;
          team_id: string;
          team_name: string;
          usage_count: number;
      }

      TeamTrainingGpuCapacityItemV1

      Per-team GPU capacity and current usage for one GPU type.

      • baseline: number

        Baseline

        Baseline GPU allocation for the team. 0 if not configured.

      • dedicated_usage_count: number

        Dedicated Usage Count

        Portion of usage_count from dedicated (on-demand) jobs.

        0
        
      • gpu_type: string

        Gpu Type

        GPU type identifier (e.g. H100, A100-40GB)

      • limit: number

        Limit

        Maximum concurrent GPUs of this type for this team

      • spot_usage_count: number

        Spot Usage Count

        Portion of usage_count from spot jobs.

        0
        
      • team_id: string

        Team Id

        Team identifier

      • team_name: string

        Team Name

        Team name

      • usage_count: number

        Usage Count

        GPUs currently in use by the team's active training jobs

    • TerminateReplicaResponse: { success: boolean }

      TerminateReplicaResponseV1

      The response to a request to terminate a replica in a deployment.

      • success: boolean

        Success

        Whether the replica was successfully terminated

        true
        
    • TrainerCheckpointTarget: "sampler" | "trainer"

      TrainerCheckpointTarget

      Whether a TrainerServerCheckpoint is loadable by the sampler or the trainer.

      SAMPLER checkpoints are consumed by the sampling server for inference;
      TRAINER checkpoints capture full trainer state for resuming training.
      Mirrored in the bt:// URI as
      ``bt://loops:<trainer_id>/(sampler_weights|weights)/<name>``.
      
    • TrainingGpuCapacityItem: {
          baseline: number;
          dedicated_usage_count: number;
          gpu_type: string;
          limit: number;
          spot_usage_count: number;
          usage_count: number;
      }

      TrainingGpuCapacityItemV1

      GPU capacity and current usage for one GPU type.

      • baseline: number

        Baseline

        Baseline GPU allocation; jobs below this threshold are expected to run immediately. 0 if not configured.

      • dedicated_usage_count: number

        Dedicated Usage Count

        Portion of usage_count from dedicated (on-demand) jobs, which run against the baseline.

        0
        
      • gpu_type: string

        Gpu Type

        GPU type identifier (e.g. H100, A100-40GB)

      • limit: number

        Limit

        Maximum concurrent GPUs of this type for this org

      • spot_usage_count: number

        Spot Usage Count

        Portion of usage_count from spot jobs, which burst into the peak and may push usage above the limit.

        0
        
      • usage_count: number

        Usage Count

        GPUs currently in use by active training jobs

    • TrainingItem: {
          billable_resource: components["schemas"]["BillableResource"];
          daily?: components["schemas"]["DailyTrainingUsage"][];
          minutes: number;
          subtotal: number | string;
      }

      TrainingItemV1

      • billable_resource: components["schemas"]["BillableResource"]

        The training job resource

      • Optionaldaily?: components["schemas"]["DailyTrainingUsage"][]

        Daily

        Daily usage breakdown

      • minutes: number

        Minutes

        Total minutes used for this billable resource

      • subtotal: number | string

        Subtotal

        Subtotal cost in dollars for this billable resource

    • TrainingJob: {
          availability_model: components["schemas"]["V1AvailabilityModel"];
          checkpoint_sync_status:
              | components["schemas"]["CheckpointSyncStatus"]
              | null;
          created_at: string;
          current_status: string;
          error_message: string
          | null;
          id: string;
          instance_type: components["schemas"]["InstanceType"];
          name: string | null;
          node_count: number;
          priority: number;
          training_project: components["schemas"]["TrainingProjectSummary"];
          training_project_id: string;
          updated_at: string;
          user: components["schemas"]["User"] | null;
      }

      TrainingJobV1

      • availability_model: components["schemas"]["V1AvailabilityModel"]

        Capacity guarantee for the job. 'dedicated' is non-preemptible on-demand capacity; 'spot' is interruptible.

        dedicated
        
      • checkpoint_sync_status: components["schemas"]["CheckpointSyncStatus"] | null

        Checkpoint sync status of the training job.

        null
        
      • created_at: string

        Created At Format: date-time

        Time the job was created in ISO 8601 format.

      • current_status: string

        Current Status

        Current status of the training job.

      • error_message: string | null

        Error Message

        Error message if the training job failed.

        null
        
      • id: string

        Id

        Unique identifier of the training job.

      • instance_type: components["schemas"]["InstanceType"]

        Instance type of the training job.

      • name: string | null

        Name

        Name of the training job.

        null
        
        gpt-oss-job
        
      • node_count: number

        Node Count

        Number of nodes the job runs on. The instance type describes a single node, so the job's total GPU count is gpu_count multiplied by node_count.

        1
        
        2
        
      • priority: number

        Priority

        Queue priority. Higher values are dequeued first. NULL is treated as 0.

        0
        
      • training_project: components["schemas"]["TrainingProjectSummary"]

        Summary of the training project.

      • training_project_id: string

        Training Project Id

        ID of the training project.

      • updated_at: string

        Updated At Format: date-time

        Time the job was updated in ISO 8601 format.

      • user: components["schemas"]["User"] | null

        The user who created the training job.

        null
        
    • TrainingJobCheckpoint: {
          base_model: string | null;
          checkpoint_id: string;
          checkpoint_type: string;
          created_at: string;
          lora_adapter_config: { [key: string]: unknown } | null;
          size_bytes: number;
          sync_status: string | null;
          training_job_id: string;
      }

      TrainingJobCheckpointV1

      A checkpoint for a training job.

      • base_model: string | null

        Base Model

        The base model of the checkpoint.

      • checkpoint_id: string

        Checkpoint Id

        The ID of the checkpoint.

      • checkpoint_type: string

        Checkpoint Type

        The type of checkpoint.

      • created_at: string

        Created At Format: date-time

        The timestamp of the checkpoint in ISO 8601 format.

      • lora_adapter_config: { [key: string]: unknown } | null

        Lora Adapter Config

        The adapter config of the checkpoint.

      • size_bytes: number

        Size Bytes

        The size of the checkpoint in bytes.

      • sync_status: string | null

        Sync Status

        Sync state of the checkpoint: SYNCING or COMPLETE.

        null
        
      • training_job_id: string

        Training Job Id

        The ID of the training job.

    • TrainingJobMetric: { timestamp: string; value: number }

      TrainingJobMetricV1

      A metric for a training job.

      • timestamp: string

        Timestamp Format: date-time

        The timestamp of the metric in ISO 8601 format.

      • value: number

        Value

        The value of the metric.

    • TrainingJobMetrics: {
          cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][];
          cpu_usage: components["schemas"]["TrainingJobMetric"][];
          ephemeral_storage: components["schemas"]["StorageMetrics"];
          gpu_memory_usage_bytes: {
              [key: string]: { timestamp: string; value: number }[];
          };
          gpu_utilization: { [key: string]: { timestamp: string; value: number }[] };
      }

      TrainingJobMetricsV1

      • cpu_memory_usage_bytes: components["schemas"]["TrainingJobMetric"][]

        Cpu Memory Usage Bytes

        The CPU memory usage for the training job. For multinode jobs, this is the CPU memory usage of the leader unless specified otherwise.

      • cpu_usage: components["schemas"]["TrainingJobMetric"][]

        Cpu Usage

        The CPU usage measured in cores. For multinode jobs, this is the CPU usage of the leader unless specified otherwise.

      • ephemeral_storage: components["schemas"]["StorageMetrics"]

        The storage usage for the ephemeral storage. For multinode jobs, this is the ephemeral storage usage of the leader unless specified otherwise.

      • gpu_memory_usage_bytes: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Memory Usage Bytes

        A map of GPU rank to memory usage for the training job. For multinode jobs, this is the memory usage of the leader unless specified otherwise.

      • gpu_utilization: { [key: string]: { timestamp: string; value: number }[] }

        Gpu Utilization

        A map of GPU rank to fractional GPU utilization. For multinode jobs, this is the GPU utilization of the leader unless specified otherwise.

    • TrainingJobNodeMetrics: { metrics: components["schemas"]["TrainingJobMetrics"]; node_id: string }

      TrainingJobNodeMetricsV1

      A set of metrics for a training job node.

      • metrics: components["schemas"]["TrainingJobMetrics"]

        The metrics for the node.

      • node_id: string

        Node Id

        The name of the node.

    • TrainingJobTombstone: { deleted: boolean; id: string; training_project_id: string }

      TrainingJobTombstoneV1

      A training job tombstone.

      • deleted: boolean

        Deleted

        Whether the training job was deleted

      • id: string

        Id

        Unique identifier of the training job

      • training_project_id: string

        Training Project Id

        Unique identifier of the training project

    • TrainingProject: {
          created_at: string;
          id: string;
          latest_job: components["schemas"]["TrainingJob"] | null;
          name: string;
          team_name: string | null;
          updated_at: string;
      }

      TrainingProjectV1

      • created_at: string

        Created At Format: date-time

        Time the training project was created in ISO 8601 format.

      • id: string

        Id

        Unique identifier of the training project

      • latest_job: components["schemas"]["TrainingJob"] | null

        Most recently created training job for the training project.

      • name: string

        Name

        Name of the training project.

      • team_name: string | null

        Team Name

        Name of the team associated with the training project.

        null
        
      • updated_at: string

        Updated At Format: date-time

        Time the training project was updated in ISO 8601 format.

    • TrainingProjectSummary: { id: string; name: string }

      TrainingProjectSummaryV1

      A summary of a training project.

      • id: string

        Id

        Unique identifier of the training project.

      • name: string

        Name

        Name of the training project.

    • TrainingProjectTombstone: { deleted: boolean; id: string }

      TrainingProjectTombstoneV1

      A training project tombstone.

      • deleted: boolean

        Deleted

        Whether the training project was deleted

      • id: string

        Id

        Unique identifier of the training project

    • TrainingUsage: {
          breakdown?: components["schemas"]["TrainingItem"][];
          credits_used: number | string;
          minutes: number;
          subtotal: number | string;
          total: number | string;
      }

      TrainingUsageV1

      • Optionalbreakdown?: components["schemas"]["TrainingItem"][]

        Breakdown

        Per-job usage breakdown

      • credits_used: number | string

        Credits Used

        Credits applied in dollars

      • minutes: number

        Minutes

        Total minutes used

      • subtotal: number | string

        Subtotal

        Subtotal cost in dollars after applying credits used

      • total: number | string

        Total

        Total cost in dollars

    • TrainingWeightAuth: {
          auth_method: components["schemas"]["AuthMethod"];
          auth_secret_name?: string | null;
          aws_assume_role_arn?: string | null;
          aws_assume_role_region?: string | null;
          aws_oidc_region?: string | null;
          aws_oidc_role_arn?: string | null;
          gcp_oidc_service_account?: string | null;
          gcp_oidc_workload_id_provider?: string | null;
      }

      TrainingWeightAuthV1

      Authentication configuration for a training weight source.

      • auth_method: components["schemas"]["AuthMethod"]

        Method used to authenticate the weight source.

      • Optionalauth_secret_name?: string | null

        Auth Secret Name

        Name of the workspace secret used for custom-secret authentication.

      • Optionalaws_assume_role_arn?: string | null

        Aws Assume Role Arn

        AWS IAM role ARN that Baseten assumes to access the weight source.

      • Optionalaws_assume_role_region?: string | null

        Aws Assume Role Region

        AWS region used for assume-role authentication.

      • Optionalaws_oidc_region?: string | null

        Aws Oidc Region

        AWS region used for OIDC authentication.

      • Optionalaws_oidc_role_arn?: string | null

        Aws Oidc Role Arn

        AWS IAM role ARN used for OIDC authentication.

      • Optionalgcp_oidc_service_account?: string | null

        Gcp Oidc Service Account

        GCP service account used for OIDC authentication.

      • Optionalgcp_oidc_workload_id_provider?: string | null

        Gcp Oidc Workload Id Provider

        GCP workload identity provider used for OIDC authentication.

    • TrussUserEnv: {
          git_info?: components["schemas"]["GitInfo"] | null;
          is_frontend_deployment?: boolean;
          is_library_deployment?: boolean;
          mypy_version?: string | null;
          pydantic_version?: string | null;
          python_version?: string | null;
          truss_client_version?: string | null;
      }

      TrussUserEnv

      This data models is used to flexibly store info alongside oracle versions.

      There is a corresponding data model in the truss client.
      In contrast, here all fields are optional for backwards compatibility with old
      clients.
      
      • Optionalgit_info?: components["schemas"]["GitInfo"] | null
      • Optionalis_frontend_deployment?: boolean

        Is Frontend Deployment

      • Optionalis_library_deployment?: boolean

        Is Library Deployment

      • Optionalmypy_version?: string | null

        Mypy Version

      • Optionalpydantic_version?: string | null

        Pydantic Version

      • Optionalpython_version?: string | null

        Python Version

      • Optionaltruss_client_version?: string | null

        Truss Client Version

    • TTSBenchmarkMetrics: {
          cost_per_audio_minute_usd?: number | null;
          max_concurrent_streams_at_rtf1?: number | null;
          ttft_ms_p50?: number | null;
          ttft_ms_p50_at_max_concurrency?: number | null;
      }

      TTSBenchmarkMetricsV1

      • Optionalcost_per_audio_minute_usd?: number | null

        Cost Per Audio Minute Usd

      • Optionalmax_concurrent_streams_at_rtf1?: number | null

        Max Concurrent Streams At Rtf1

      • Optionalttft_ms_p50?: number | null

        Ttft Ms P50

      • Optionalttft_ms_p50_at_max_concurrency?: number | null

        Ttft Ms P50 At Max Concurrency

    • UpdateAutoscalingScheduleSettings: {
          delete_schedules?: string[];
          schedules?: (
              | components["schemas"]["AutoscalingScheduleUpsert"]
              | components["schemas"]["OneTimeAutoscalingScheduleUpsert"]
          )[];
          timezone?: string
          | null;
      }

      UpdateAutoscalingScheduleSettingsV1

      Partial mutation of an environment's autoscaling schedule collection.

      • Optionaldelete_schedules?: string[]

        Delete Schedules

        Stable identifiers of schedules to delete. To clear all schedules, include every existing schedule identifier.

      • Optionalschedules?: (
            | components["schemas"]["AutoscalingScheduleUpsert"]
            | components["schemas"]["OneTimeAutoscalingScheduleUpsert"]
        )[]

        Schedules

        Complete schedules to create or replace. Existing schedules omitted from this list are unchanged.

      • Optionaltimezone?: string | null

        Timezone

        IANA timezone shared by the resulting collection. Omission preserves the current timezone; null is allowed only when deleting every schedule.

    • UpdateAutoscalingSettings: {
          autoscaling_window?: number | null;
          concurrency_target?: number | null;
          max_replica?: number | null;
          max_scale_down_rate?: number | null;
          min_replica?: number | null;
          scale_down_delay?: number | null;
          target_in_flight_tokens?: number | null;
          target_utilization_percentage?: number | null;
      }

      UpdateAutoscalingSettingsV1

      A request to update autoscaling settings for a deployment. All fields are optional, and we only update ones passed in.

      • Optionalautoscaling_window?: number | null

        Autoscaling Window

        Timeframe of traffic considered for autoscaling decisions

        600
        
      • Optionalconcurrency_target?: number | null

        Concurrency Target

        Number of requests per replica before scaling up

        2
        
      • Optionalmax_replica?: number | null

        Max Replica

        Maximum number of replicas

        7
        
      • Optionalmax_scale_down_rate?: number | null

        Max Scale Down Rate

        Maximum percentage of replicas that can be removed per autoscaling window (1–50). E.g. 20 means at most 20% of replicas are removed per window.

        20
        
      • Optionalmin_replica?: number | null

        Min Replica

        Minimum number of replicas

        0
        
      • Optionalscale_down_delay?: number | null

        Scale Down Delay

        Waiting period before scaling down any active replica

        120
        
      • Optionaltarget_in_flight_tokens?: number | null

        Target In Flight Tokens

        Target number of in-flight tokens for autoscaling decisions. Early access only.

        40000
        
      • Optionaltarget_utilization_percentage?: number | null

        Target Utilization Percentage

        Target utilization percentage for scaling up/down.

        70
        
    • UpdateAutoscalingSettingsResponse: {
          message: string;
          status: components["schemas"]["UpdateAutoscalingSettingsStatus"];
      }

      UpdateAutoscalingSettingsResponseV1

      The response to a request to update autoscaling settings.

      • message: string

        Message

        A message describing the status of the request to update autoscaling settings

      • status: components["schemas"]["UpdateAutoscalingSettingsStatus"]

        Status of the request to update autoscaling settings

    • UpdateAutoscalingSettingsStatus: "ACCEPTED" | "QUEUED" | "UNCHANGED"

      UpdateAutoscalingSettingsStatusV1

      The status of a request to update autoscaling settings.

    • UpdateChainEnvironmentRequest: { promotion_settings?: components["schemas"]["UpdatePromotionSettings"] | null }

      UpdateChainEnvironmentRequestV1

      A request to update a chain environment.

      • Optionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | null

        Promotion settings for the environment

        {
        * "promotion_cleanup_strategy": null,
        * "ramp_up_duration_seconds": 600,
        * "ramp_up_while_promoting": true,
        * "redeploy_on_promotion": null,
        * "rolling_deploy": null,
        * "rolling_deploy_config": null
        * }
    • UpdateChainEnvironmentResponse: { ok: boolean }

      UpdateChainEnvironmentResponseV1

      A response to update a chain environment.

      • ok: boolean

        Ok

        Whether the update was successful

    • UpdateChainletEnvironmentAutoscalingSettingsRequest: {
          updates: components["schemas"]["ChainletEnvironmentAutoscalingSettingsUpdate"][];
      }

      UpdateChainletEnvironmentAutoscalingSettingsRequestV1

      A request to update the autoscaling settings for a multiple chainlets in an environment. If a chainlet name doesn't exist, an error is returned.

      • updates: components["schemas"]["ChainletEnvironmentAutoscalingSettingsUpdate"][]

        Updates

        Mapping of chainlet name to the desired chainlet autoscaling settings. If the chainlet name doesn't exist, an error is returned.

        [
        {
        "autoscaling_settings": {
        "autoscaling_window": 800,
        "concurrency_target": 4,
        "max_replica": 3,
        "max_scale_down_rate": null,
        "min_replica": 2,
        "scale_down_delay": 63,
        "target_in_flight_tokens": null,
        "target_utilization_percentage": null
        },
        "chainlet_name": "HelloWorld"
        }
        ]
        [
        {
        "autoscaling_settings": {
        "autoscaling_window": null,
        "concurrency_target": null,
        "max_replica": null,
        "max_scale_down_rate": null,
        "min_replica": 0,
        "scale_down_delay": null,
        "target_in_flight_tokens": null,
        "target_utilization_percentage": null
        },
        "chainlet_name": "HelloWorld"
        },
        {
        "autoscaling_settings": {
        "autoscaling_window": null,
        "concurrency_target": null,
        "max_replica": null,
        "max_scale_down_rate": null,
        "min_replica": 0,
        "scale_down_delay": null,
        "target_in_flight_tokens": null,
        "target_utilization_percentage": null
        },
        "chainlet_name": "RandInt"
        }
        ]
    • UpdateChainletEnvironmentInstanceTypeRequest: { updates: components["schemas"]["ChainletEnvironmentInstanceTypeUpdate"][] }

      UpdateChainletEnvironmentInstanceTypeRequestV1

      A request to update the instance types for chainlets in an environment. Multiples updates can be made in one request. The updates will be processed in batch and a new deployment will be created, deployed and promoted into the environment.

      • updates: components["schemas"]["ChainletEnvironmentInstanceTypeUpdate"][]

        Updates

        Mapping of chainlet name to the desired chainlet instance type. If the chainlet name doesn't exist, an error is returned.

        [
        {
        "chainlet_name": "HelloWorld",
        "instance_type_id": "1x4"
        },
        {
        "chainlet_name": "RandInt",
        "instance_type_id": "A10G:2x24x96"
        }
        ]
    • UpdateChainletEnvironmentInstanceTypeResponse: {
          chain_deployment: components["schemas"]["ChainDeployment"] | null;
          chainlet_environment_settings: components["schemas"]["ChainletEnvironmentSettings"][];
          requires_redeployment: boolean;
      }

      UpdateChainletEnvironmentInstanceTypeResponseV1

      A response to update the environment settings for a chainlet. If updating the instance type resulted in a re-deployment, requires_redeployment will be True and the resulting deployment will be returned in the chain_deployment field.

      • chain_deployment: components["schemas"]["ChainDeployment"] | null

        The chain deployment resulting from the resource update, if any.

      • chainlet_environment_settings: components["schemas"]["ChainletEnvironmentSettings"][]

        Chainlet Environment Settings

        The updated chainlet environment settings

      • requires_redeployment: boolean

        Requires Redeployment

        Whether the resource update requires a re-deployment to update the instance type.

    • UpdateDeploymentRequest: { name?: string | null }

      UpdateDeploymentRequestV1

      A request to update a deployment.

      • Optionalname?: string | null

        Name

        New name for the deployment, unique among the model's deployments. Only alphanumeric characters, hyphens, underscores, and periods are allowed.

        my-deployment
        
    • UpdateEndpointRequest: { targets?: components["schemas"]["EndpointTargetRequest"][] | null }

      UpdateEndpointRequestV1

      PATCH body. Replaces the endpoint's full target list. The slug is immutable after creation; to change it, create a new endpoint and delete this one.

      • Optionaltargets?: components["schemas"]["EndpointTargetRequest"][] | null

        Targets

        The endpoint's upstream targets. Exactly one target is supported at this time.

        [
        {
        "environment_name": "staging",
        "model_id": "3kZ9xqd",
        "provider": "BASETEN",
        "target_model": "custom/model-name"
        }
        ]
        [
        {
        "provider": "OPENAI",
        "secret_id": "3kZ9xqd",
        "target_model": "gpt-4o"
        }
        ]
        [
        {
        "base_url": "https://my-vllm.example.com",
        "provider": "OPENAI_COMPATIBLE",
        "secret_id": "3kZ9xqd",
        "target_model": "my-model"
        }
        ]
    • UpdateEnvironmentGroupManageAccess: { is_restricted: boolean; user_ids?: string[] }

      UpdateEnvironmentGroupManageAccessV1

      Manage-access settings to apply to an environment group.

      • is_restricted: boolean

        Is Restricted

        Whether to restrict this environment to a specific set of users.

      • Optionaluser_ids?: string[]

        User Ids

        IDs of users granted manage access while restricted. Only meaningful when is_restricted is true.

    • UpdateEnvironmentGroupRequest: {
          manage_access?:
              | components["schemas"]["UpdateEnvironmentGroupManageAccess"]
              | null;
      }

      UpdateEnvironmentGroupRequestV1

      A request to update an existing environment group.

      • Optionalmanage_access?: components["schemas"]["UpdateEnvironmentGroupManageAccess"] | null

        Manage-access settings to apply. Omit to leave manage access unchanged.

    • UpdateEnvironmentRequest: {
          autoscaling_schedule_settings?:
              | components["schemas"]["UpdateAutoscalingScheduleSettings"]
              | null;
          autoscaling_settings?: | components["schemas"]["UpdateAutoscalingSettings"]
          | null;
          promotion_settings?: | components["schemas"]["UpdatePromotionSettings"]
          | null;
          request_backpressure_settings?: | components["schemas"]["UpdateRequestBackpressureSettings"]
          | null;
      }

      UpdateEnvironmentRequestV1

      A request to update an environment.

      • Optionalautoscaling_schedule_settings?: components["schemas"]["UpdateAutoscalingScheduleSettings"] | null

        Partial autoscaling schedule collection update. Omitted collection fields and existing schedules are unchanged; each submitted schedule is a complete create or replacement.

        {
        * "schedules": [
        * {
        * "autoscaling_settings": {
        * "autoscaling_window": null,
        * "concurrency_target": null,
        * "max_replica": 8,
        * "max_scale_down_rate": null,
        * "min_replica": 2,
        * "scale_down_delay": null,
        * "target_in_flight_tokens": null,
        * "target_utilization_percentage": null
        * },
        * "cadence": "DAILY",
        * "enabled": true,
        * "end_hour": 10,
        * "end_minute": 0,
        * "name": "weekday-peak",
        * "start_hour": 8,
        * "start_minute": 0,
        * "weekdays": [
        * "MONDAY",
        * "TUESDAY",
        * "WEDNESDAY",
        * "THURSDAY",
        * "FRIDAY"
        * ]
        * }
        * ],
        * "timezone": "America/Los_Angeles"
        * }
        {
        * "delete_schedules": [
        * "schedule-id"
        * ]
        * }
      • Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | null

        Autoscaling settings for the environment

        {
        * "autoscaling_window": 800,
        * "concurrency_target": 3,
        * "max_replica": 2,
        * "max_scale_down_rate": null,
        * "min_replica": 1,
        * "scale_down_delay": 60,
        * "target_in_flight_tokens": null,
        * "target_utilization_percentage": null
        * }
      • Optionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | null

        Promotion settings for the environment

        {
        * "promotion_cleanup_strategy": null,
        * "ramp_up_duration_seconds": 600,
        * "ramp_up_while_promoting": true,
        * "redeploy_on_promotion": true,
        * "rolling_deploy": null,
        * "rolling_deploy_config": null
        * }
      • Optionalrequest_backpressure_settings?: components["schemas"]["UpdateRequestBackpressureSettings"] | null

        Request backpressure settings for the environment.

        {
        * "policy": "REJECT_ON_FULL"
        * }
    • UpdateEnvironmentResponse: {
          environment: components["schemas"]["Environment"];
          message: string;
          status: components["schemas"]["UpdateAutoscalingSettingsStatus"];
      }

      UpdateEnvironmentResponseV1

      The response to a request to update an environment's settings.

      • environment: components["schemas"]["Environment"]

        The environment after the update, matching the shape returned by GET.

      • message: string

        Message

        Deprecated. Kept for legacy autoscaling-only update operation behavior.

      • status: components["schemas"]["UpdateAutoscalingSettingsStatus"]

        Deprecated. Kept for legacy autoscaling-only update operation behavior.

    • UpdateGroupMetadata: { name?: string | null }

      UpdateGroupMetadataV1

      • Optionalname?: string | null

        Name

        Optional display name for the group.

        Acme prod
        
    • UpdateGroupRequest: {
          metadata?: components["schemas"]["UpdateGroupMetadata"] | null;
          models?: components["schemas"]["ModelConfig"][] | null;
      }

      UpdateGroupRequestV1

      • Optionalmetadata?: components["schemas"]["UpdateGroupMetadata"] | null

        Mutable group metadata.

        {
        * "name": "Acme Prod"
        * }
      • Optionalmodels?: components["schemas"]["ModelConfig"][] | null

        Models

        Per-model rate and usage limit configuration.

    • UpdateLibraryListingRequest: {
          display_name?: string | null;
          is_public?: boolean | null;
          metadata?: components["schemas"]["LibraryListingMetadata"] | null;
          trending?: boolean | null;
      }

      UpdateLibraryListingRequestV1

      Request to update a library listing.

      • Optionaldisplay_name?: string | null

        Display Name

        New display name for the library listing

      • Optionalis_public?: boolean | null

        Is Public

        Whether the listing is publicly accessible

      • Optionalmetadata?: components["schemas"]["LibraryListingMetadata"] | null

        Model-level metadata for the listing. When provided, replaces the stored metadata. Unknown fields are rejected.

      • Optionaltrending?: boolean | null

        Trending

        Whether the listing is trending

    • UpdateLibraryListingVersionRequest: {
          allow_truss_download?: boolean | null;
          benchmark?: components["schemas"]["BenchmarkSnapshot"] | null;
          is_live?: boolean | null;
      }

      UpdateLibraryListingVersionRequestV1

      Request to update a library listing version.

      • Optionalallow_truss_download?: boolean | null

        Allow Truss Download

        Whether users deploying this model can download the Truss

      • Optionalbenchmark?: components["schemas"]["BenchmarkSnapshot"] | null

        Benchmark snapshot for this version. When provided, replaces the stored benchmark.

      • Optionalis_live?: boolean | null

        Is Live

        Whether this version should be the live version. Setting to true demotes the current live version.

    • UpdatePromotionSettings: {
          promotion_cleanup_strategy?:
              | components["schemas"]["PromotionCleanupStrategy"]
              | null;
          ramp_up_duration_seconds?: number
          | null;
          ramp_up_while_promoting?: boolean | null;
          redeploy_on_promotion?: boolean | null;
          rolling_deploy?: boolean | null;
          rolling_deploy_config?:
              | components["schemas"]["UpdateRollingDeployConfig"]
              | null;
      }

      UpdatePromotionSettingsV1

      Promotion settings for model promotion

      • Optionalpromotion_cleanup_strategy?: components["schemas"]["PromotionCleanupStrategy"] | null

        The cleanup strategy to use after a promotion completes.

        SCALE_TO_ZERO
        
      • Optionalramp_up_duration_seconds?: number | null

        Ramp Up Duration Seconds

        Duration of the ramp up in seconds

        600
        
      • Optionalramp_up_while_promoting?: boolean | null

        Ramp Up While Promoting

        Whether to ramp up traffic while promoting

        true
        
      • Optionalredeploy_on_promotion?: boolean | null

        Redeploy On Promotion

        Whether to deploy on all promotions. Enabling this flag allows model code to safely handle environment-specific logic. When a deployment is promoted, a new deployment will be created with a copy of the image.

        true
        
      • Optionalrolling_deploy?: boolean | null

        Rolling Deploy

        Whether the environment should rely on rolling deploy orchestration.

        true
        
      • Optionalrolling_deploy_config?: components["schemas"]["UpdateRollingDeployConfig"] | null

        Rolling deploy configuration for promotions

    • UpdateRequestBackpressureSettings: { policy?: components["schemas"]["RequestBackpressurePolicy"] | null }

      UpdateRequestBackpressureSettingsV1

      A request to update request backpressure settings.

      • Optionalpolicy?: components["schemas"]["RequestBackpressurePolicy"] | null

        Backpressure policy to apply. Null indicates no policy (on update, clears an existing one).

        REJECT_ON_FULL
        
    • UpdateRollingDeployConfig: {
          max_surge_percent?: number | null;
          max_unavailable_percent?: number | null;
          replica_overhead_percent?: number | null;
          rolling_deploy_strategy?:
              | components["schemas"]["RollingDeployStrategy"]
              | null;
          stabilization_time_seconds?: number
          | null;
      }

      UpdateRollingDeployConfigV1

      Rolling deploy config for promoting chains and oracles

      • Optionalmax_surge_percent?: number | null

        Max Surge Percent

        The maximum surge percentage for rolling deploys.

        25
        
      • Optionalmax_unavailable_percent?: number | null

        Max Unavailable Percent

        The maximum unavailable percentage for rolling deploys.

        10
        
      • Optionalreplica_overhead_percent?: number | null

        Replica Overhead Percent

        The replica overhead percentage for rolling deploys.

        0
        
      • Optionalrolling_deploy_strategy?: components["schemas"]["RollingDeployStrategy"] | null

        The rolling deploy strategy to use for promotions.

        REPLICA
        
      • Optionalstabilization_time_seconds?: number | null

        Stabilization Time Seconds

        The stabilization time in seconds for rolling deploys.

        300
        
    • UpdateTrainingJobRequest: {
          availability_model?: components["schemas"]["V1AvailabilityModel"] | null;
          priority?: number | null;
      }

      UpdateTrainingJobRequestV1

      A request to update mutable fields on a training job.

      Every field is optional so a caller can patch one without the other, but at least
      one must be provided: an empty body has nothing to apply.
      
      • Optionalavailability_model?: components["schemas"]["V1AvailabilityModel"] | null

        New capacity guarantee for a PENDING training job. 'dedicated' runs on on-demand capacity that is not preempted. 'spot' runs on interruptible capacity that may be preempted; the user is responsible for checkpointing their own progress. Only jobs in the PENDING state can have their availability model changed.

        spot
        
      • Optionalpriority?: number | null

        Priority

        New queue priority for a PENDING training job. Higher values are dequeued first. Only jobs in the PENDING state can have their priority changed.

        0
        
        10
        
        100
        
    • UpdateTrainingJobResponse: { training_job: components["schemas"]["TrainingJob"] }

      UpdateTrainingJobResponseV1

      A response to updating a training job.

    • UpsertSecretRequest: { name: string; value: string }

      UpsertSecretRequestV1

      A request to create or update a Baseten secret by name.

      • name: string

        Name

        Name of the new or existing secret

        my_secret
        
      • value: string

        Value

        Value of the secret

        my_secret_value
        
    • UpsertTrainingProject: { name: string }

      UpsertTrainingProjectV1

      Fields that can be upserted on a training project.

      • name: string

        Name

        Name of the training project.

        My Training Project
        
    • UpsertTrainingProjectRequest: { training_project: components["schemas"]["UpsertTrainingProject"] }

      UpsertTrainingProjectRequestV1

      A request to upsert a training project.

      • training_project: components["schemas"]["UpsertTrainingProject"]

        The training project to upsert.

    • UpsertTrainingProjectResponse: { training_project: components["schemas"]["TrainingProject"] }

      UpsertTrainingProjectResponseV1

      A response to upserting a training project.

      • training_project: components["schemas"]["TrainingProject"]

        The upserted training project.

    • UsageDimension: "api_key" | "user" | "model"

      UsageDimensionV1

    • UsageLimit: {
          threshold: number;
          type: components["schemas"]["LimitType"];
          unit: components["schemas"]["UsageLimitUnit"];
      }

      UsageLimitV1

      • threshold: number

        Threshold

        The threshold for the usage limit

        10000000
        
      • type: components["schemas"]["LimitType"]

        The type of the usage limit

        REQUEST
        
        TOKEN
        
      • unit: components["schemas"]["UsageLimitUnit"]

        The unit of the usage limit

        DAY
        
    • UsageLimitUnit: "DAY"

      UsageLimitUnitV1

    • UsageSummary: {
          dedicated_usage: components["schemas"]["DedicatedUsage"] | null;
          model_apis_usage: components["schemas"]["ModelApisUsage"] | null;
          training_usage: components["schemas"]["TrainingUsage"] | null;
      }

      UsageSummaryV1

      Billing usage summary for the requested date range.

      • dedicated_usage: components["schemas"]["DedicatedUsage"] | null

        Dedicated model serving usage

        null
        
      • model_apis_usage: components["schemas"]["ModelApisUsage"] | null

        Model APIs usage

        null
        
      • training_usage: components["schemas"]["TrainingUsage"] | null

        Training usage

        null
        
    • User: { email: string | null }

      UserV1

      A user.

      • email: string | null

        Email

        Email of the user.

        null
        
    • UserInfo: {
          email: string | null;
          name: string | null;
          user_id: string;
          workspace_name: string | null;
      }

      UserInfoV1

      A Baseten user.

      • email: string | null

        Email

        Email address of the user

        null
        
      • name: string | null

        Name

        Display name of the user

        null
        
      • user_id: string

        User Id

        Unique identifier for the user

      • workspace_name: string | null

        Workspace Name

        Name of the user's workspace

        null
        
    • UsersResponse: {
          items: components["schemas"]["UserInfo"][];
          pagination: components["schemas"]["PaginationResponse"];
      }

      UsersResponseV1

      A page of users in the caller's workspace.

    • V1AvailabilityModel: "dedicated" | "spot"

      V1AvailabilityModel

      Capacity guarantee under which a training job is scheduled.

      ``DEDICATED`` is on-demand capacity that is not preempted (the default). ``SPOT`` is
      interruptible capacity that may be preempted; the user is responsible for checkpointing
      their own progress. A managed/resumable model where the platform handles
      checkpoint/resume on its own is intentionally not defined yet; it is planned for a
      future milestone.
      
    • V1InteractiveSessionAuthProvider: "github" | "microsoft"

      V1InteractiveSessionAuthProvider

    • V1InteractiveSessionProvider: "vs_code" | "cursor" | "ssh"

      V1InteractiveSessionProvider

    • V1InteractiveSessionTrigger: "on_startup" | "on_failure" | "on_demand"

      V1InteractiveSessionTrigger

    • ValidateLoopsCheckpointRequest: { checkpoint_path: string }

      ValidateLoopsCheckpointRequestV1

      Request body for POST /v1/loops/checkpoints/validate.

      • checkpoint_path: string

        Checkpoint Path

        bt:// URI of a sampler checkpoint. Form: bt://loops:<run_id>/sampler_weights/<checkpoint_name>.

        bt://loops:k4q95w5/sampler_weights/step-100
        
    • ValidateLoopsCheckpointResponse: Record<string, unknown>

      ValidateLoopsCheckpointResponseV1

      Response for POST /v1/loops/checkpoints/validate. Empty on success; inaccessible or malformed paths raise 400.

    • VertexTargetConfig: { location: string; project_id: string }

      VertexTargetConfigV1

      • location: string

        Location

        Google Cloud location.

        global
        
      • project_id: string

        Project Id

        Google Cloud project ID or project number.

        my-gcp-project
        
        464036093014
        
    • Volume: {
          head: components["schemas"]["VolumeVersionSummary"] | null;
          name: string;
          namespace: string;
          sequence: number;
          tag_count: number;
          tags: components["schemas"]["VolumeTag"][];
          updated_at: string;
          version_ref: string;
          versions_alive: number;
          versions_tombstoned: number;
          versions_untagged: number;
      }

      VolumeV1

      • head: components["schemas"]["VolumeVersionSummary"] | null

        Version that the reserved head tag points at, which a reference with no tag or digest resolves to. Null when the volume has no head, or when your API key cannot read it.

      • name: string

        Name

        Name of the volume, in lowercase.

      • namespace: string

        Namespace

        Namespace the volume belongs to, in lowercase.

      • sequence: number

        Sequence

        Revision counter for the volume, incremented on every commit and tag change. Use it to detect that a volume changed.

      • tag_count: number

        Tag Count

        Total number of tags on the volume, which can exceed the length of tags when your API key cannot read all of them.

      • tags: components["schemas"]["VolumeTag"][]

        Tags

        Tags on the volume that your API key can read.

      • updated_at: string

        Updated At Format: date-time

        When the volume last changed, in ISO 8601 format.

      • version_ref: string

        Version Ref

        Full address of the volume, as bdn:<namespace>/<volume>. Paste this into the bdn.mounts section of a config.yaml.

      • versions_alive: number

        Versions Alive

        Number of versions that have not been deleted.

      • versions_tombstoned: number

        Versions Tombstoned

        Number of versions that have been deleted.

      • versions_untagged: number

        Versions Untagged

        Number of versions that no tag points at.

    • VolumeTag: { digest: string; name: string }

      VolumeTagV1

      • digest: string

        Digest

        Digest of the version the tag points at, as b3:<hex>.

      • name: string

        Name

        Tag name. Tags are case-sensitive.

    • VolumeTokenScope: "PULL" | "INSPECT" | "PUSH" | "TAG"

      VolumeTokenScopeV1

      Capability a volume token grants.

      - ``PULL``: read volume data.
      - ``INSPECT``: read volume metadata without data access.
      - ``PUSH``: upload and commit volume versions.
      - ``TAG``: move or remove tags.
      
    • VolumeVersion: {
          created_at: string;
          delete_after: string | null;
          digest: string;
          is_head: boolean;
          lifecycle: string;
          namespace: string;
          sequence: number | null;
          tags: string[];
          tombstoned_at: string | null;
          total_size_bytes: number | null;
          version_ref: string;
          volume: string;
      }

      VolumeVersionV1

      • created_at: string

        Created At Format: date-time

        When the version was committed, in ISO 8601 format.

      • delete_after: string | null

        Delete After

        When the version stops being restorable, in ISO 8601 format. Null unless the lifecycle is TOMBSTONED.

      • digest: string

        Digest

        Content digest of the version, as b3:<hex>.

      • is_head: boolean

        Is Head

        Whether the reserved head tag points at this version.

      • lifecycle: string

        Lifecycle

        Lifecycle state of the version, for example ALIVE or TOMBSTONED.

      • namespace: string

        Namespace

        Namespace the volume belongs to, in lowercase.

      • sequence: number | null

        Sequence

        Revision the version was committed at. Null for versions committed before the volume service recorded it.

      • tags: string[]

        Tags

        Tags pointing at this version that your API key can read.

      • tombstoned_at: string | null

        Tombstoned At

        When the version was deleted, in ISO 8601 format. Null unless the lifecycle is TOMBSTONED.

      • total_size_bytes: number | null

        Total Size Bytes

        Total size of the version's files in bytes. Null when not recorded.

      • version_ref: string

        Version Ref

        Full address of this version, as bdn:<namespace>/<volume>@<digest>. Paste this into the bdn.mounts section of a config.yaml to pin to it.

      • volume: string

        Volume

        Name of the volume, in lowercase.

    • VolumeVersionDetail: {
          created_at: string;
          delete_after: string | null;
          digest: string;
          entry_count: number | null;
          is_head: boolean;
          lifecycle: string;
          namespace: string;
          sequence: number | null;
          tags: string[];
          tombstoned_at: string | null;
          total_size_bytes: number | null;
          version_ref: string;
          volume: string;
          volume_sequence: number;
      }

      VolumeVersionDetailV1

      One version, with the fields only a single-version read reports.

      • created_at: string

        Created At Format: date-time

        When the version was committed, in ISO 8601 format.

      • delete_after: string | null

        Delete After

        When the version stops being restorable, in ISO 8601 format. Null unless the lifecycle is TOMBSTONED.

      • digest: string

        Digest

        Content digest of the version, as b3:<hex>.

      • entry_count: number | null

        Entry Count

        Number of files in the version. Null when not recorded.

      • is_head: boolean

        Is Head

        Whether the reserved head tag points at this version.

      • lifecycle: string

        Lifecycle

        Lifecycle state of the version, for example ALIVE or TOMBSTONED.

      • namespace: string

        Namespace

        Namespace the volume belongs to, in lowercase.

      • sequence: number | null

        Sequence

        Revision the version was committed at. Null for versions committed before the volume service recorded it.

      • tags: string[]

        Tags

        Tags pointing at this version that your API key can read.

      • tombstoned_at: string | null

        Tombstoned At

        When the version was deleted, in ISO 8601 format. Null unless the lifecycle is TOMBSTONED.

      • total_size_bytes: number | null

        Total Size Bytes

        Total size of the version's files in bytes. Null when not recorded.

      • version_ref: string

        Version Ref

        Full address of this version, as bdn:<namespace>/<volume>@<digest>. Paste this into the bdn.mounts section of a config.yaml to pin to it.

      • volume: string

        Volume

        Name of the volume, in lowercase.

      • volume_sequence: number

        Volume Sequence

        Revision of the volume as a whole when this version was read. Pass it as expected_sequence on a later delete to make that delete conditional on the volume not having changed since.

    • VolumeVersionSummary: { created_at: string; digest: string; total_size_bytes: number }

      VolumeVersionSummaryV1

      • created_at: string

        Created At Format: date-time

        When the version was committed, in ISO 8601 format.

      • digest: string

        Digest

        Content digest of the version, as b3:<hex>.

      • total_size_bytes: number

        Total Size Bytes

        Total size of the version's files in bytes.