ActivateResponseV1
No Op
Success
ActiveJobAtSubmitV1
Instance Type Name
Status At Submit
Status Set At Format: date-time
Total Gpus
Training Job Id
Training Job Name
Workload Plane Name
APIKeyV1
Api Key
APIKeyCategory
APIKeyInfoV1
Model Ids
Name
Prefix
Team Name
APIKeyOwnerV1
Name
User Id
APIKeysV1
Keys
APIKeyTombstoneV1
Prefix
AuditLogActorV1
Api Key Name
Api Key Prefix
AuditLogActorTypeV1
AuditLogApiKeyTypeV1
AuditLogEntryV1
Client Name
Client Session Id
Client Version
Created Format: date-time
Event Data
Id
AuditLogEventApiKeyCreatedV1
Api Key Id
Prefix
AuditLogEventApiKeyDeletedV1
Api Key Id
Prefix
AuditLogEventAutoscalingScheduleActionV1
AuditLogEventAutoscalingScheduleChangeV1
Schedule Id
AuditLogEventAutoscalingScheduleSettingsV1
Autoscaling Window
Cadence
Concurrency Target
Enabled
End At
End Hour
End Minute
Max Replica
Max Scale Down Rate
Min Replica
Scale Down Delay
Schedule Name
Start At
Start Hour
Start Minute
Target In Flight Tokens
Target Utilization Percentage
Timezone
Weekdays
AuditLogEventAutoscalingSettingsV1
Autoscaling Window
Concurrency Target
Max Replica
Max Scale Down Rate
Min Replica
Scale Down Delay
Target In Flight Tokens
Target Utilization Percentage
AuditLogEventChainDeletedV1
Chain Deployment Name
Chain Id
Chain Name
AuditLogEventChainDeployedV1
Chain Deployment Id
Chain Deployment Name
Chain Id
Chain Name
Is Primary
Publish
AuditLogEventChainDeploymentActivatedV1
Chain Deployment Id
Chain Deployment Name
Chain Id
Chain Name
AuditLogEventChainDeploymentDeactivatedV1
Chain Deployment Id
Chain Deployment Name
Chain Id
Chain Name
AuditLogEventChainDeploymentDeletedV1
Chain Deployment Id
Chain Id
Chain Name
Deployment Name
AuditLogEventChainDeploymentPromotedV1
Chain Deployment Id
Chain Deployment Name
Chain Id
Chain Name
Environment Id
Environment Name
AuditLogEventChainEnvironmentCreatedV1
Chain Id
Chain Name
Environment Name
Ramp Up Duration Seconds
Ramp Up While Promoting
Redeploy On Promotion
AuditLogEventChainEnvironmentUpdatedV1
Chain Id
Chain Name
Environment Name
Ramp Up Duration Seconds
Ramp Up While Promoting
Redeploy On Promotion
AuditLogEventChainletAutoscalingSettingsChangedV1
Autoscaling Window
Chain Deployment Id
Chain Deployment Name
Chain Id
Chain Name
Chainlet Id
Chainlet Name
Concurrency Target
Max Replica
Max Scale Down Rate
Min Replica
Scale Down Delay
Target In Flight Tokens
Target Utilization Percentage
AuditLogEventChainletInstanceTypeChangedV1
Chain Deployment Id
Chain Deployment Name
Chain Id
Chain Name
Chainlet Id
Chainlet Name
Instance Type Name
AuditLogEventDirectoryGroupRoleUpdatedV1
Directory Group Id
Directory Group Name
New Role Name
Team Id
Team Name
AuditLogEventEnvironmentCreatedV1
Autoscaling Window
Concurrency Target
Deployment Type
Environment Name
Max Replica
Max Scale Down Rate
Max Surge Percent
Max Unavailable Percent
Min Replica
Model Id
Model Name
Promotion Cleanup Strategy
Ramp Up Duration Seconds
Ramp Up Step Size
Ramp Up While Promoting
Redeploy On Promotion
Replica Overhead Percent
Request Backpressure Policy
Rolling Deploy
Rolling Deploy Strategy
Scale Down Delay
Stabilization Time Seconds
Target In Flight Tokens
Target Utilization Percentage
AuditLogEventEnvironmentDeletedV1
Environment Name
Model Id
Model Name
AuditLogEventEnvironmentSettingsV1
Autoscaling Window
Concurrency Target
Max Replica
Max Scale Down Rate
Max Surge Percent
Max Unavailable Percent
Min Replica
Promotion Cleanup Strategy
Ramp Up Duration Seconds
Ramp Up Step Size
Ramp Up While Promoting
Redeploy On Promotion
Replica Overhead Percent
Request Backpressure Policy
Rolling Deploy
Rolling Deploy Strategy
Scale Down Delay
Stabilization Time Seconds
Target In Flight Tokens
Target Utilization Percentage
AuditLogEventEnvironmentUpdatedV1
Autoscaling Window
Concurrency Target
Deployment Type
Environment Name
Max Replica
Max Scale Down Rate
Max Surge Percent
Max Unavailable Percent
Min Replica
Model Id
Model Name
Promotion Cleanup Strategy
Ramp Up Duration Seconds
Ramp Up Step Size
Ramp Up While Promoting
Redeploy On Promotion
Replica Overhead Percent
Request Backpressure Policy
Rolling Deploy
Rolling Deploy Strategy
Scale Down Delay
Schedules
Stabilization Time Seconds
Target In Flight Tokens
Target Utilization Percentage
AuditLogEventGatewayEndpointCreatedV1
Gateway Endpoint Id
Slug
AuditLogEventGatewayEndpointDeletedV1
Gateway Endpoint Id
Slug
AuditLogEventGatewayEndpointUpdatedV1
Gateway Endpoint Id
Previous Slug
Slug
AuditLogEventModelDeletedV1
Model Id
Model Name
AuditLogEventModelDeployedV1
Deployment Id
Deployment Name
Environment Name
Model Id
Model Name
Publish
Scale Previous To Zero
Trusted
AuditLogEventModelDeploymentActivatedV1
Deployment Id
Deployment Name
Model Id
Model Name
AuditLogEventModelDeploymentAutoscalingSettingsChangedV1
Autoscaling Window
Concurrency Target
Deployment Id
Deployment Name
Deployment Type
Max Replica
Max Scale Down Rate
Min Replica
Model Id
Model Name
Scale Down Delay
Schedules
Target In Flight Tokens
Target Utilization Percentage
AuditLogEventModelDeploymentDeactivatedV1
Deployment Id
Deployment Name
Model Id
Model Name
AuditLogEventModelDeploymentDeletedV1
Deployment Id
Deployment Name
Model Id
Model Name
AuditLogEventModelDeploymentInstanceTypeChangedV1
Deployment Id
Deployment Name
Instance Type Name
Model Id
Model Name
AuditLogEventModelDeploymentPromotedV1
Deployment Id
Deployment Name
Environment Id
Environment Name
Model Id
Model Name
AuditLogEventModelDeploymentRequestBackpressureSettingsChangedV1
Deployment Id
Deployment Name
Model Id
Model Name
Policy
Previous Policy
AuditLogEventModelDeploymentRetriedV1
Deployment Id
Deployment Name
Model Id
Model Name
Retried
AuditLogEventModelPromotionControlActionV1
Deployment Id
Deployment Name
Environment Id
Environment Name
Model Id
Model Name
AuditLogEventReplicaTerminatedV1
Deployment Id
Deployment Name
Model Id
Model Name
Replica Id
AuditLogEventRequireGroupBasedAdminsEnabledV1
Organization Id
AuditLogEventSecretDeletedV1
Secret Id
Secret Name
AuditLogEventSecretUpdatedV1
Secret Id
Secret Name
AuditLogEventSshCertificateSignedV1
Expires At
Project Id
Proxy Address
Replica Id
Workload Id
Workload Type
AuditLogEventTypeV1
AuditLogEventTypeGroupV1
AuditLogEventUserInvitedV1
Invited User Email
Role Name
AuditLogEventUserJoinedOrganizationV1
New User Email
User Id
AuditLogEventUserRemovedV1
Removed User Email
AuditLogEventUserRoleUpdatedV1
New Role Name
User Email
User Id
AuditLogEventUserTeamRoleUpdatedV1
New Role Name
Team Id
Team Name
User Email
User Id
AuditLogEventVolumeDeletedV1
Namespace
Versions Deleted
Volume Name
Volume Ref
AuditLogEventVolumeVersionDeletedV1
Digest
Namespace
Version
Volume Name
Volume Ref
AuditLogEventVolumeVersionRestoredV1
Digest
Namespace
Version
Volume Name
Volume Ref
AuditLogEventWebhookSigningSecretCreatedV1
Webhook Signing Secret Id
AuditLogEventWebhookSigningSecretDeletedV1
Webhook Signing Secret Id
AuditLogEventWebhookSigningSecretRotatedV1
Webhook Signing Secret Id
AuditLogPromotionControlActionV1
AuditLogSortDirectionV1
AuditLogSourceV1
AuthCodeV1
Auth Code
Auth Url
URL where the user should enter the auth code (e.g., 'https://github.com/login/device').
Expires At
Generated At
Replica Id
Session Id
Tunnel Name
Working Directory
AuthMethod
AutoscalingScheduleV1
Enabled
End Hour
End Minute
Id
Name
Start Hour
Start Minute
Weekdays
AutoscalingScheduleSettingsV1
Autoscaling Window
Concurrency Target
Max Replica
Max Scale Down Rate
Min Replica
Scale Down Delay
Target In Flight Tokens
Target Utilization Percentage
AutoscalingScheduleSettingsRequestV1
Autoscaling Window
Concurrency Target
Max Replica
Max Scale Down Rate
Min Replica
Scale Down Delay
Target In Flight Tokens
Target Utilization Percentage
AutoscalingScheduleStateV1
Schedule Id
AutoscalingScheduleUpsertV1
Enabled
Optionalend_hour?: number | nullEnd Hour
End Minute
Optionalid?: string | nullId
Name
Optionalstart_hour?: number | nullStart Hour
Start Minute
Weekdays
AutoscalingScheduleWeekdayV1
AutoscalingSettingsV1
Autoscaling Window
Concurrency Target
Max Replica
Max Scale Down Rate
Min Replica
Scale Down Delay
Target In Flight Tokens
Target Utilization Percentage
AwsAssumeRoleV1
Baseten Role Arn
External Id
AwsAssumeRoleDockerAuthV1
Region
Role Arn
AWSCredentialsV1
Aws Access Key Id
Aws Secret Access Key
Aws Session Token
AwsIamDockerAuthV1
AwsOidcDockerAuthV1
Region
Role Arn
BasetenLatestCheckpointConfig
Optionaljob_id?: string | nullJob Id
Optionalproject_name?: string | nullProject Name
BasetenNamedCheckpointConfig
Checkpoint Name
Optionaljob_id?: string | nullJob Id
Optionalproject_name?: string | nullProject Name
BenchmarkSnapshotV1
Optionalembedding?: components["schemas"]["EmbeddingBenchmarkMetrics"] | nullOptionalllm?: components["schemas"]["LLMBenchmarkMetrics"] | nullMeasured At Format: date
Optionalprofile?: string | nullProfile
Optionalreplicas?: number | nullReplicas
Run Id
Optionaltts?: components["schemas"]["TTSBenchmarkMetrics"] | nullBillableResourceV1
Base Model
Environment Name
Id
Instance Type
Is Deleted
Model Id
Model Name
Name
Team Id
Team Name
BucketWidth
CancelPromotionResponseV1
Message
CancelPromotionStatusV1
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
Last Modified Format: date-time
Max Gpus
Min Gpus
ChainV1
Created At Format: date-time
Deployments Count
Id
Name
Team Name
ChainDeploymentV1
Chain Id
Chainlets
Created At Format: date-time
Environment
Id
ChainDeploymentsV1
Deployments
ChainDeploymentTombstoneV1
Chain Id
Deleted
Id
ChainEnvironmentV1
Chain Id
Chainlet Settings
Created At Format: date-time
Name
ChainletV1
Active Replica Count
Id
Instance Type Name
Name
ChainletEnvironmentAutoscalingSettingsUpdateV1
Chainlet Name
ChainletEnvironmentInstanceTypeUpdateV1
Chainlet Name
Instance Type Id
ChainletEnvironmentSettingsV1
Chainlet Name
ChainletEnvironmentSettingsRequestV1
Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | nullChainlet Name
Optionalinstance_type_id?: stringInstance Type Id
ChainMetadataV1
Chain Deployment Id
Chain Id
Chain Name
ChainsV1
Chains
ChainTombstoneV1
Deleted
Id
CheckpointFile
Last Modified
Node Rank
Relative File Name
Size Bytes
Url
CheckpointSyncStatus
CreateApiKeyForGroupRequestV1
Optionalname?: string | nullName
CreateApiKeyForGroupResponseV1
Api Key
Name
Prefix
CreateAPIKeyRequestV1
Optionalmodel_ids?: string[] | nullModel Ids
Optionalname?: string | nullName
Optionalteam_id?: string | nullTeam Id
CreateChainEnvironmentRequestV1
Optionalchainlet_settings?: components["schemas"]["ChainletEnvironmentSettingsRequest"][] | nullChainlet 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
Optionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | nullCreateDeploymentPatchRequestV1
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
CreateDeploymentPatchResponseV1
CreatedModelDeploymentV1
CreateEndpointRequestV1
Optionalregion?: components["schemas"]["SharedEndpointRegion"]Slug
Targets
CreateEnvironmentRequestV1
Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | nullName
Optionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | nullOptionalrequest_backpressure_settings?: components["schemas"]["UpdateRequestBackpressureSettings"] | nullCreateGroupHierarchyV1
Optionallimit_enforcement?: components["schemas"]["LimitEnforcement"] | nullOptionalparent_group_id?: string | nullParent Group Id
CreateGroupRequestV1
Models
CreateJobWeightConfigV1
Optionalallow_patterns?: string[] | nullAllow Patterns
Optionalauth?: components["schemas"]["TrainingWeightAuth"] | null{
* "auth_method": "AWS_OIDC",
* "aws_oidc_region": "us-east-1",
* "aws_oidc_role_arn": "arn:aws:iam::123456789012:role/weights-access"
* }
Optionalauth_secret_name?: string | nullAuth Secret Name
Optionalignore_patterns?: string[] | nullIgnore Patterns
Mount Location
Source
CreateLibraryListingRequestV1
Optionalclosed_source?: booleanClosed Source
Display Name
Optionalis_public?: booleanIs Public
User Defined Id
CreateLibraryListingVersionRequestV1
Optionalallow_truss_download?: booleanAllow Truss Download
Optionalclosed_source?: booleanClosed Source
Optionaldisplay_name?: string | nullDisplay Name
Optionalis_public?: booleanIs Public
Oracle Version Id
Version Tag
CreateLLMModelRequestV1
Optionaladditional_autoscaling_config?: { [key: string]: unknown } | nullAdditional Autoscaling Config
Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | nullOptionalenvironment_variables?: { [key: string]: unknown }Environment Variables
Optionalllm_config?: { [key: string]: unknown }Llm Config
Optionalllm_version?: string | nullLlm Version
Optionalmetadata?: { [key: string]: unknown } | nullMetadata
Optionalmodel_metadata?: { [key: string]: unknown } | nullModel Metadata
Name
Optionalregion?: string | nullRegion
Resources
Optionalweights?: { [key: string]: unknown }[] | nullWeights
CreateLLMModelVersionRequestV1
Optionaladditional_autoscaling_config?: { [key: string]: unknown } | nullAdditional Autoscaling Config
Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | nullOptionalenvironment_variables?: { [key: string]: unknown }Environment Variables
Optionalllm_config?: { [key: string]: unknown }Llm Config
Optionalllm_version?: string | nullLlm Version
Optionalmetadata?: { [key: string]: unknown } | nullMetadata
Optionalmodel_metadata?: { [key: string]: unknown } | nullModel Metadata
Optionalregion?: string | nullRegion
Resources
Optionalweights?: { [key: string]: unknown }[] | nullWeights
CreateLoopsRunRequestV1
Optionalavailability_model?: components["schemas"]["V1AvailabilityModel"]Base Model
Optionallora_rank?: numberLora Rank
Optionalmax_seq_len?: number | nullMax Seq Len
Optionalname?: string | nullName
Optionalpath?: string | nullPath
Optionalreplicas?: numberReplicas
Optionalreuse_from_run_id?: string | nullReuse From Run Id
Optionalreuse_from_session_id?: string | nullReuse From Session Id
Optionalscale_down_delay_seconds?: numberScale Down Delay Seconds
Optionalseed?: number | nullSeed
Session Id
CreateLoopsRunResponseV1
CreateLoopsSamplerRequestV1
Optionalbase_model?: string | nullBase Model
Optionalmax_seq_length?: number | nullMax Seq Length
Optionalmodel_path?: string | nullModel Path
Optionalreuse_from_session_id?: string | nullReuse From Session Id
Optionalrun_id?: string | nullRun Id
Session Id
CreateLoopsSamplerResponseV1
CreateLoopsSessionResponseV1
CreateModelDeploymentRequestV1
Source
CreateModelRequestV1
Source
CreateTrainingJobV1
Optionalcompute?: components["schemas"]["CreateTrainingJobCompute"]Optionalenable_baseten_workdir?: booleanEnable Baseten Workdir
Optionalinteractive_session?: components["schemas"]["InteractiveSessionConfig"] | nullOptionalname?: string | nullName
Optionalpriority?: number | nullPriority
Optionalruntime?: components["schemas"]["CreateTrainingJobRuntime"]{
* "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"] | nullOptionalweights?: components["schemas"]["CreateJobWeightConfig"][]Weights
CreateTrainingJobAcceleratorV1
Accelerator
Count
CreateTrainingJobCacheConfig
Optionalenable_legacy_hf_mount?: booleanEnable Legacy Hf Mount
Optionalenabled?: booleanEnabled
Optionalmount_base_path?: stringMount Base Path
Optionalrequire_cache_affinity?: booleanRequire Cache Affinity
CreateTrainingJobCheckpointingConfig
Optionalcheckpoint_path?: string | nullCheckpoint Path
Optionalenabled?: booleanEnabled
Optionalvolume_size_gib?: number | nullVolume Size Gib
CreateTrainingJobComputeV1
Optionalaccelerator?: components["schemas"]["CreateTrainingJobAccelerator"] | nullOptionalavailability_model?: components["schemas"]["V1AvailabilityModel"]Optionalcpu_count?: numberCpu Count
Optionalmemory?: stringMemory
Optionalnode_count?: numberNode Count
CreateTrainingJobImageV1
Base Image
Optionaldocker_auth?: components["schemas"]["DockerAuth"] | nullCreateTrainingJobRequestV1
CreateTrainingJobResponseV1
CreateTrainingJobRuntimeV1
Optionalartifacts?: components["schemas"]["CreateTrainingJobS3Artifact"][]Artifacts
Optionalcache_config?: components["schemas"]["CreateTrainingJobCacheConfig"] | nullOptionalcheckpointing_config?: components["schemas"]["CreateTrainingJobCheckpointingConfig"]Optionalenable_cache?: boolean | nullEnable Cache
Optionalenvironment_variables?: { [key: string]: string | { name: string } }Environment Variables
Optionalload_checkpoint_config?: components["schemas"]["LoadCheckpointConfig"] | nullOptionalstart_commands?: string[]Start Commands
CreateTrainingJobS3Artifact
S3 Bucket
S3 Key
CreateVolumeTokenRequestV1
Optionalcorrelation_id?: string | nullCorrelation Id
Namespaces
Scopes
Volumes
CreateVolumeTokenResponseV1
Bdn Endpoint
Expires At Format: date-time
Namespaces
Scopes
Token
Volumes
DailyDedicatedUsageV1
Compute Cost
Date Format: date
Inference Requests
Minutes
Subtotal
Surcharge Cost
DailyModelApiUsageV1
Cached Input Tokens
Date Format: date
Input Tokens
Output Tokens
Subtotal
DailyTrainingUsageV1
Date Format: date
Minutes
Subtotal
DeactivateLoopsDeploymentResponseV1
Base Model
Id
DeactivateLoopsRunResponseV1
Base Model
Id
DeactivateResponseV1
No Op
Success
DedicatedItemV1
Compute Cost
Optionaldaily?: components["schemas"]["DailyDedicatedUsage"][]Daily
Inference Requests
Minutes
Subtotal
Surcharge Cost
DedicatedUsageV1
Optionalbreakdown?: components["schemas"]["DedicatedItem"][]Breakdown
Credits Used
Minutes
Subtotal
Total
DeleteVolumeRequestV1
Optionalexpected_sequence?: number | nullExpected Sequence
DeleteVolumeResponseV1
Name
Namespace
Versions Deleted
Volume Sequence
DeleteVolumeVersionRequestV1
Optionalexpected_sequence?: number | nullExpected Sequence
DeleteVolumeVersionResponseV1
Delete After Format: date-time
Digest
Lifecycle
Namespace
Version Ref
Volume
Volume Sequence
DeploymentV1
Active Replica Count
Created At Format: date-time
Environment
Id
Instance Type Name
Is Development
Is Production
Labels
Model Id
Name
DeploymentArchivePayloadV1
Config
Optionalcreate_environment_if_missing?: booleanCreate 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 | nullDeploy Timeout Minutes
Optionaldeployment_name?: string | nullDeployment Name
Optionalenvironment_name?: string | nullEnvironment Name
Optionalis_development?: booleanIs Development
Optionallabels?: { [key: string]: unknown } | nullLabels
Optionalpreserve_env_instance_type?: booleanPreserve Env Instance Type
Optionalraw_config?: string | nullRaw Config
Optionalregion?: string | nullRegion
Optionaluser_env?: { [key: string]: unknown } | nullUser Env
DeploymentArchiveSourceV1
Optionals3_key?: string | nullS3 Key
DeploymentConfigOutputFormat
DeploymentConfigResponseV1
Config
Raw Config
DeploymentPatchActionV1
DeploymentPatchOpConfigV1
Config
Optionalpath?: stringPath
DeploymentPatchOpEnvVarV1
Name
Optionalvalue?: string | nullValue
DeploymentPatchOpExternalDataV1
Item
DeploymentPatchOpModelCodeV1
Optionalcontent?: string | nullContent
Optionalcontent_bytes?: string | nullContent Bytes
Optionalhot_reload?: booleanHot Reload
Path
DeploymentPatchOpPackageV1
Optionalcontent?: string | nullContent
Optionalcontent_bytes?: string | nullContent Bytes
Path
DeploymentPatchOpPythonRequirementV1
Requirement
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
Content Hashes
Optionalrequirements?: string[]Requirements
DeploymentPatchPointWithHashV1
Config
Content Hashes
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
DeploymentsV1
Deployments
DeploymentStatusV1
DeploymentTombstoneV1
Deleted
Id
Model Id
DockerAuthV1
Optionalaws_assume_role_docker_auth?: components["schemas"]["AwsAssumeRoleDockerAuth"] | nullOptionalaws_iam_docker_auth?: components["schemas"]["AwsIamDockerAuth"] | nullOptionalaws_oidc_docker_auth?: components["schemas"]["AwsOidcDockerAuth"] | nullOptionalgcp_oidc_docker_auth?: components["schemas"]["GcpOidcDockerAuth"] | nullOptionalgcp_service_account_json_docker_auth?: components["schemas"]["GcpServiceAccountJsonDockerAuth"] | nullRegistry
Optionalregistry_secret_docker_auth?: components["schemas"]["RegistrySecretDockerAuth"] | nullDockerAuthType
DownloadDeploymentResponseV1
Download Url
DownloadTrainingJobResponseV1
Artifact Presigned Urls
EffectiveModelConfigV1
Optionalrate_limits?: components["schemas"]["EffectiveRateLimit"][]Rate Limits
Slug
Optionalusage_limits?: components["schemas"]["EffectiveUsageLimit"][]Usage Limits
EffectiveRateLimitV1
Source Group
Threshold
EffectiveUsageLimitV1
Source Group
Threshold
EmbeddingBenchmarkMetricsV1
Optionale2e_latency_ms_p50?: number | nullE2E Latency Ms P50
Optionale2e_latency_ms_p99?: number | nullE2E Latency Ms P99
Optionalinput_tokens_per_sec?: number | nullInput Tokens Per Sec
Optionalrequests_per_sec?: number | nullRequests Per Sec
EndpointV1
Created At Format: date-time
Id
Slug
Targets
Updated At Format: date-time
EndpointsResponseV1
Items
EndpointTargetV1
Base Url
Environment Name
Model Id
Secret Id
Target Model
EndpointTargetRequestV1
Optionalbase_url?: string | nullBase Url
Optionalenvironment_name?: string | nullEnvironment Name
Optionalmodel_id?: string | nullModel Id
Optionalsecret_id?: string | nullSecret Id
Optionaltarget_model?: string | nullTarget Model
Optionalvertex_config?: components["schemas"]["VertexTargetConfig"] | nullEndpointTombstoneV1
Id
Slug
EnvironmentV1
Created At Format: date-time
Model Id
Name
EnvironmentAutoscalingSchedulesV1
Schedules
Timezone
EnvironmentGroupV1
Name
Team Id
Team Name
EnvironmentGroupManageAccessV1
Is Restricted
Optionalusers?: components["schemas"]["EnvironmentGroupUser"][]Users
EnvironmentGroupsV1
Items
EnvironmentGroupUserV1
Name
User Id
EnvironmentsV1
Environments
EnvironmentTombstoneV1
Deleted
Model Id
Name
FileSummary
File Type
Modified
Path
Permissions
Size Bytes
GatewayEventV1
Apikeyprefix
Externalentityid
Idempotencykey
Modelslug
Requestid
Timestamp
Type
GatewayEventsResponseV1
Items
GatewayEventTokensV1
Cachedinputtokens
Inputtokens
Outputtokens
GatewayKeyInfoV1
Name
Prefix
GatewayProvider
GcpOidcDockerAuthV1
Service Account
Workload Identity Provider
GcpServiceAccountJsonDockerAuthV1
Optionalchain_deployment_ids?: string[]Chain Deployment Ids
Optionalcursor?: string | nullCursor
Optionaldeployment_ids?: string[]Deployment Ids
Optionaldirection?: components["schemas"]["AuditLogSortDirection"]Optionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalenvironment_names?: string[]Environment Names
Optionalevent_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][]Event Type Groups
Optionallimit?: numberLimit
Optionalsearch?: string | nullSearch
Optionalsources?: components["schemas"]["AuditLogSource"][]Sources
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionaluser_ids?: string[]User Ids
GetAuthCodesResponseV1
Auth Codes
Optionalapi_key_prefixes?: string[]Api Key Prefixes
Optionalcursor?: string | nullCursor
Optionalend_date?: string | nullEnd Date
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?: numberLimit
Optionalmodels?: string[]Models
Optionalservice_tiers?: string[]Service Tiers
Optionalstart_date?: string | nullStart Date
Optionaluser_ids?: string[]User Ids
End Date Format: date-time
Start Date Format: date-time
GetBlobCredentialsResponseV1
S3 Bucket
S3 Key
GetCacheSummaryResponseV1
File Summaries
Project Id
Timestamp
Optionalchain_deployment_ids?: string[]Chain Deployment Ids
Optionalcursor?: string | nullCursor
Optionaldeployment_ids?: string[]Deployment Ids
Optionaldirection?: components["schemas"]["AuditLogSortDirection"]Optionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalenvironment_names?: string[]Environment Names
Optionalevent_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][]Event Type Groups
Optionallimit?: numberLimit
Optionalsearch?: string | nullSearch
Optionalsources?: components["schemas"]["AuditLogSource"][]Sources
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionaluser_ids?: string[]User Ids
Optionalcomponent?: string | nullComponent
Optionaldirection?: components["schemas"]["SortOrder"] | nullOptionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalexcludes?: string[]Excludes
Optionalincludes?: string[]Includes
Optionallimit?: number | nullLimit
Optionalmin_level?: components["schemas"]["LogLevel"] | nullOptionalreplica?: string | nullReplica
Optionalrequest_id?: string | nullRequest Id
Optionalsearch_pattern?: string | nullSearch Pattern
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
GetDeploymentLogsRequestV1
Optionalcomponent?: string | nullComponent
Optionaldirection?: components["schemas"]["SortOrder"] | nullOptionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalexcludes?: string[]Excludes
Optionalincludes?: string[]Includes
Optionallimit?: number | nullLimit
Optionalmin_level?: components["schemas"]["LogLevel"] | nullOptionalreplica?: string | nullReplica
Optionalrequest_id?: string | nullRequest Id
Optionalsearch_pattern?: string | nullSearch Pattern
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
GetDeploymentPatchesStateResponseV1
Optionalapi_keys?: string[]Api Keys
Optionalcursor?: string | nullCursor
Optionalend_time?: string | nullEnd Time
Optionalexternal_entity_ids?: string[]External Entity Ids
Optionallimit?: number | nullLimit
Optionalstart_time?: string | nullStart Time
GetLogsResponseV1
Logs
GetLoopsCapabilitiesResponseV1
Supported Models
Optionalpage_size?: numberPage Size
Optionalpage_token?: numberPage Token
Optionalbase_model?: string | nullBase Model
Optionalcheckpoint_path?: string | nullCheckpoint Path
Optionalrun_id?: string | nullRun Id
GetLoopsDeploymentMetricsRequestV1
Optionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalstep_seconds?: number | nullStep Seconds
Optionaltime_divisor_seconds?: number | nullTime Divisor Seconds
GetLoopsDeploymentMetricsResponseV1
Deployment Id
GetLoopsDeploymentResponseV1
Optionalpage_size?: numberPage Size
Optionalpage_token?: string | nullPage Token
Optionaldirection?: components["schemas"]["SortOrder"] | nullOptionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionallimit?: number | nullLimit
Optionalmin_level?: components["schemas"]["LogLevel"] | nullOptionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalscope?: string | nullScope
GetLoopsRunResponseV1
Optionalbase_model?: string | nullBase Model
Optionalrun_id?: string | nullRun Id
Optionalscope?: string | nullScope
GetLoopsSamplerResponseV1
Optionalscope?: string | nullScope
GetLoopsSessionResponseV1
GetLoopsUserConfigResponseV1
Optionaladded_only?: booleanAdded Only
Optionalcursor?: string | nullCursor
Optionallimit?: numberLimit
Optionalapi_keys?: string[]Api Keys
Optionalbucket_width?: components["schemas"]["BucketWidth"]Optionalcursor?: string | nullCursor
Optionalend_time?: string | nullEnd Time
Optionalgroup_by?: components["schemas"]["UsageDimension"][]Group By
Optionallimit?: number | nullLimit
Optionalmodels?: string[]Models
Optionalstart_time?: string | nullStart Time
Optionaluser_ids?: string[]User Ids
GetModelMetricsResponseV1
End Epoch Millis
Metric Descriptors
Metric Values
Start Epoch Millis
Step Seconds
Optionalchain_deployment_ids?: string[]Chain Deployment Ids
Optionalcursor?: string | nullCursor
Optionaldeployment_ids?: string[]Deployment Ids
Optionaldirection?: components["schemas"]["AuditLogSortDirection"]Optionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalenvironment_names?: string[]Environment Names
Optionalevent_type_groups?: components["schemas"]["AuditLogEventTypeGroup"][]Event Type Groups
Optionallimit?: numberLimit
Optionalsearch?: string | nullSearch
Optionalsources?: components["schemas"]["AuditLogSource"][]Sources
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionaluser_ids?: string[]User Ids
Optionaloutput_format?: components["schemas"]["DeploymentConfigOutputFormat"]Optionalcomponent?: string | nullComponent
Optionaldirection?: components["schemas"]["SortOrder"] | nullOptionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalexcludes?: string[]Excludes
Optionalincludes?: string[]Includes
Optionallimit?: number | nullLimit
Optionalmin_level?: components["schemas"]["LogLevel"] | nullOptionalreplica?: string | nullReplica
Optionalrequest_id?: string | nullRequest Id
Optionalsearch_pattern?: string | nullSearch Pattern
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalend_epoch_millis?: number | nullEnd Epoch Millis
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"]Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalname?: string | nullName
Optionalcomponent?: string | nullComponent
Optionaldirection?: components["schemas"]["SortOrder"] | nullOptionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalexcludes?: string[]Excludes
Optionalincludes?: string[]Includes
Optionallimit?: number | nullLimit
Optionalmin_level?: components["schemas"]["LogLevel"] | nullOptionalreplica?: string | nullReplica
Optionalrequest_id?: string | nullRequest Id
Optionalsearch_pattern?: string | nullSearch Pattern
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalend_epoch_millis?: number | nullEnd Epoch Millis
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"]Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalname?: string | nullName
Optionalbase_model?: string | nullBase Model
Optionalrun_id?: string | nullRun Id
Optionalscope?: string | nullScope
Optionalscope?: string | nullScope
Optionalname?: string | nullName
Optionalname?: string | nullName
GetTrainingGpuCapacityResponseV1
Gpu Capacities
Optionalteam_gpu_capacities?: components["schemas"]["TeamTrainingGpuCapacityItem"][]Team Gpu Capacities
GetTrainingJobCheckpointFilesResponseV1
Next Page Token
Presigned Urls
Total Count
GetTrainingJobCheckpointsResponseV1
Checkpoints
GetTrainingJobLogsRequestV1
Optionaldirection?: components["schemas"]["SortOrder"] | nullOptionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionallimit?: number | nullLimit
Optionalmin_level?: components["schemas"]["LogLevel"] | nullOptionalstart_epoch_millis?: number | nullStart Epoch Millis
GetTrainingJobMetricsRequestV1
Optionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalstep_seconds?: number | nullStep Seconds
GetTrainingJobMetricsResponseV1
Cpu Memory Usage Bytes
Cpu Usage
Gpu Memory Usage Bytes
Gpu Utilization
Per Node Metrics
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
Events
Events Window End Format: date-time
Gpu Type
Pending Ahead At Submit
Pending Seconds
Released At
Requested Gpus
Submitted At Format: date-time
Target Job Id
Target Job Name
GetTrainingJobResponseV1
GetTrainingProjectResponseV1
Optionalpage_size?: numberPage Size
Optionalpage_token?: numberPage Token
Optionaldirection?: components["schemas"]["SortOrder"] | nullOptionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionallimit?: number | nullLimit
Optionalmin_level?: components["schemas"]["LogLevel"] | nullOptionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalend_epoch_millis?: number | nullEnd Epoch Millis
Optionalstart_epoch_millis?: number | nullStart Epoch Millis
Optionalstep_seconds?: number | nullStep Seconds
Optionalcursor?: string | nullCursor
Optionalemail?: string | nullOptionallimit?: numberLimit
Optionalcursor?: string | nullCursor
Optionallimit?: numberLimit
Optionalcursor?: string | nullCursor
Optionallimit?: numberLimit
Namespace
Optionalinclude_tombstoned?: booleanInclude Tombstoned
GitInfo
Commits Since Tag
Has Uncommitted Changes
Latest Commit Sha
Latest Tag
GroupV1
Created At Format: date-time
Optionaleffective_models?: components["schemas"]["EffectiveModelConfig"][]Effective Models
Id
Optionalmodels?: components["schemas"]["ModelConfig"][]Models
GroupHierarchyV1
Parent Group Id
GroupMetadataV1
External Entity Id
Optionalname?: string | nullName
GroupsResponseV1
Items
InferenceVolumeByStatusDatapointV1
Status 2Xx
Status 4Xx
Status 5Xx
Timestamp Format: date-time
InProgressPromotionV1
Error Message
Percent Traffic To New Version
Rolling Deploy
InProgressPromotionStatusV1
InstanceTypeV1
Gpu Count
Gpu Memory Limit Mib
Gpu Type
Id
Memory Limit Mib
Millicpu Limit
Name
InstanceTypePricesV1
Instance Types
InstanceTypesV1
Instance Types
InstanceTypeWithPriceV1
Price
InteractiveSessionV1
Auth Code
Auth Code Generated At
Auth Provider
Auth Url
Authenticated At
Expires At
Id
Pod Name
Session Provider
Timeout Minutes
Trigger
Tunnel Name
Working Directory
InteractiveSessionConfigV1
Optionalauth_provider?: components["schemas"]["V1InteractiveSessionAuthProvider"]Optionalsession_provider?: components["schemas"]["V1InteractiveSessionProvider"]Optionaltimeout_minutes?: numberTimeout Minutes
Optionaltrigger?: components["schemas"]["V1InteractiveSessionTrigger"]KeysForGroupResponseV1
Items
LibraryListingV1
Closed Source
Created At Format: date-time
Display Name
Is Public
Modified At Format: date-time
Trending
User Defined Id
LibraryListingMetadataV1
Optionalcontext_length?: number | nullContext Length
Optionaldescription?: string | nullDescription
Optionalinput_modalities?: components["schemas"]["LibraryListingModality"][]Input Modalities
License
Optionalmodel_api_slug?: string | nullModel Api Slug
Optionaloutput_modalities?: components["schemas"]["LibraryListingModality"][]Output Modalities
Optionalparameter_count?: number | nullParameter Count
Optionalpublisher?: string | nullPublisher
Optionalrelease_date?: string | nullRelease Date
Optionaltrending?: booleanTrending
Optionalvariant?: string | nullVariant
LibraryListingModality
LibraryListingsV1
Listings
LibraryListingSourceV1
Optionaldeployed_model_name?: string | nullDeployed Model Name
Lab Display Name
User Defined Listing Id
LibraryListingTombstoneV1
Deleted
User Defined Id
LibraryListingVersionV1
Allow Truss Download
Created At Format: date-time
Is Live
Modified At Format: date-time
Oracle Version Id
Version Tag
LibraryListingVersionsV1
Versions
LibraryListingVersionTombstoneV1
Deleted
Version Tag
LimitEnforcementV1
LimitTypeV1
ListAuditLogsResponseV1
Items
ListLoopsCheckpointsResponseV1
Checkpoints
ListLoopsDeploymentsResponseV1
Deployments
ListLoopsRunsResponseV1
Runs
ListLoopsSamplersResponseV1
Samplers
ListTrainingJobsResponseV1
Training Jobs
ListTrainingProjectsResponseV1
Training Projects
ListVolumeNamespacesResponseV1
Items
ListVolumesResponseV1
Items
ListVolumeVersionsResponseV1
Versions
Volume Sequence
LLMBenchmarkMetricsV1
Optionalcost_per_1m_tokens_usd?: number | nullCost Per 1M Tokens Usd
Optionalmax_concurrent_users_at_50ms_tpot?: number | nullMax Concurrent Users At 50Ms Tpot
Optionaloutput_tokens_per_sec_per_user_p50?: number | nullOutput Tokens Per Sec Per User P50
Optionalrequests_per_sec_p50?: number | nullRequests Per Sec P50
Optionalttft_ms_p50?: number | nullTtft Ms P50
LLMModelHandleV1
Hostname
Instance Type Name
Model Id
Version Id
LoadCheckpointConfig
Optionalcheckpoints?: (Checkpoints
Optionaldownload_folder?: stringDownload Folder
Optionalenabled?: booleanEnabled
LogV1
Message
Replica
Request Id
Timestamp
LogLevelV1
LoopsCheckpointV1
Base Model
Checkpoint Id
Checkpoint Type
Created At Format: date-time
Id
Lora Adapter Config
Run Id
Size Bytes
Sync Status
LoopsCheckpointConfig
Checkpoint Name
Run Id
Optionaltarget?: "trainer" | "sampler"Target
LoopsCheckpointFilesResponseV1
Next Page Token
Presigned Urls
Total Count
LoopsDebugArchiveFilesResponseV1
Next Page Token
Presigned Urls
LoopsDeploymentV1
Active Run Id
Base Model
Base Url
Created At Format: date-time
Id
Latest Run Id
Node Count
LoopsDeploymentMetricsV1
Concurrent Requests
Cpu Memory Usage Bytes
Cpu Usage
Gpu Memory Usage Bytes
Gpu Utilization
Inference Volume
Inference Volume By Status
Per Node Metrics
Response Time Stats
LoopsDeploymentNodeMetricsV1
Cpu Memory Usage Bytes
Cpu Usage
Gpu Memory Usage Bytes
Gpu Utilization
Node Id
LoopsDeploymentStatusV1
LoopsRunV1
Base Model
Base Url
Created At Format: date-time
Deployment Id
Id
Name
Session Id
LoopsRunStatusV1
LoopsRunStatusNameV1
LoopsSamplerV1
Base Model
Base Url
Created At Format: date-time
Deployment Id
Id
Model Id
Node Count
LoopsSamplerStatusV1
LoopsSessionV1
Id
LoopsUserConfigV1
Sampler Accelerator Priority
Trainer Accelerator Priority
ModelV1
Created At Format: date-time
Deployments Count
Development Deployment Id
Id
Instance Type Name
Name
Production Deployment Id
Team Name
ModelAPIV1
Context Length
Cost Per Million Input Tokens
Cost Per Million Output Tokens
Description
Display Name
Invoke Url
Model Family
Name
Rate Limits
Release Date Format: date
ModelApiCostDimensionV1
ModelApiItemV1
Cached Input Tokens
Optionaldaily?: components["schemas"]["DailyModelApiUsage"][]Daily
Input Tokens
Model Family
Model Name
Output Tokens
Subtotal
ModelAPIOrgDetailsV1
Added At Format: date-time
Last Used At
ModelApisCostBucketV1
Date Format: date
Optionalresults?: components["schemas"]["ModelApisCostResult"][]Results
ModelApisCostResultV1
Api Key Prefixes
Model
Service Tier
Subtotal
User Id
ModelApisCostsResponseV1
Items
ModelAPIsResponseV1
Items
ModelApisUsageV1
Optionalbreakdown?: components["schemas"]["ModelApiItem"][]Breakdown
Credits Used
Subtotal
Total
ModelApisUsageBucketV1
End Time Format: date-time
Optionalresults?: components["schemas"]["ModelApisUsageResult"][]Results
Start Time Format: date-time
ModelApisUsageResponseV1
Items
ModelApisUsageResultV1
Api Key Prefix
Cached Input Tokens
Input Tokens
Model
Output Tokens
Request Count
Uncached Input Tokens
User Id
ModelArchiveSourceV1
Optionaldisable_archive_download?: booleanDisable Archive Download
Name
Optionals3_key?: string | nullS3 Key
ModelConfigV1
Optionalrate_limits?: components["schemas"]["RateLimit"][]Rate Limits
Slug
Optionalusage_limits?: components["schemas"]["UsageLimit"][]Usage Limits
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.
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
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.
ModelMetricModeV1
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).
ModelMetricValueSetV1
Start Epoch Millis
Values
ModelsV1
Models
ModelTombstoneV1
Deleted
Id
LoopsDeploymentStatus
OneTimeAutoscalingScheduleV1
Enabled
End At Format: date-time
Id
Name
Start At Format: date-time
OneTimeAutoscalingScheduleUpsertV1
Enabled
End At Format: date-time
Optionalid?: string | nullId
Name
Start At Format: date-time
OrderByV1
Field
Order
OrganizationInfoV1
Created At Format: date-time
Name
Org Id
PaginationResponseV1
Cursor
Has More
PatchInteractiveSessionRequestV1
Optionaltimeout_minutes?: number | nullTimeout Minutes
Optionaltrigger?: components["schemas"]["V1InteractiveSessionTrigger"] | nullPatchInteractiveSessionResponseV1
Message
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[] | nullSampler Accelerator Priority
Optionaltrainer_accelerator_priority?: string[] | nullTrainer Accelerator Priority
PatchLoopsUserConfigResponseV1
PatchTeamTrainingGpuCapacityRequestV1
Gpu Type
Max Gpus
Team Id
PatchTeamTrainingGpuCapacityResponseV1
PendingJobAheadAtSubmitV1
Instance Type Name
Priority
Requested Gpus
Submitted At Format: date-time
Training Job Id
Training Job Name
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`).
Optionaldry_run?: booleanDry Run
Optionalmodel_id?: string | nullModel Id
Optionalname?: string | nullName
Optionalteam_id?: string | nullTeam Id
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).
S3 Bucket
S3 Key
S3 Region
PromoteRequestV1
Optionalpreserve_env_instance_type?: booleanPreserve Env Instance Type
Optionalscale_down_previous_production?: booleanScale Down Previous Production
PromoteToChainEnvironmentRequestV1
Deployment Id
Optionalscale_down_previous_deployment?: booleanScale Down Previous Deployment
PromoteToEnvironmentRequestV1
Deployment Id
Optionalpreserve_env_instance_type?: booleanPreserve Env Instance Type
Optionalscale_down_previous_deployment?: booleanScale Down Previous Deployment
PromotionCleanupStrategyV1
PromotionSettingsV1
Ramp Up Duration Seconds
Ramp Up While Promoting
Redeploy On Promotion
Rolling Deploy
QueueEventV1
Created Format: date-time
Event Message
Exit Code
Status
TrainingJobStatus.Name value
Training Job Id
Training Job Name
RateLimitV1
Threshold
RateLimitUnitV1
RecreateTrainingJobResponseV1
RegionV1
Display Name
Slug
RegionsV1
Regions
RegisterAPIKeyRequestV1
Key
Optionalname?: string | nullName
RegisterAPIKeyResponseV1
Ok
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'.
RequestBackpressurePolicyV1
RequestBackpressureSettingsV1
ResourceKind
ResponseTimeDatapointV1
P50
P95
P99
Timestamp Format: date-time
RestoreVolumeVersionRequestV1
Optionalexpected_sequence?: number | nullExpected Sequence
RestoreVolumeVersionResponseV1
Digest
Lifecycle
Namespace
Version Ref
Volume
Volume Sequence
RetryDeploymentResponseV1
Reason
Retried
RollingDeployConfigV1
Max Surge Percent
Max Unavailable Percent
Replica Overhead Percent
Stabilization Time Seconds
RollingDeployStrategyV1
SearchTrainingJobsRequestV1
Optionaljob_id?: string | nullJob Id
Optionalorder_by?: components["schemas"]["OrderBy"][]Order By
Optionalproject_id?: string | nullProject Id
Optionalstatuses?: string[] | nullStatuses
SearchTrainingJobsResponseV1
Training Jobs
SecretV1
Created At Format: date-time
Id
Name
Team Name
SecretReferenceV1
Name
SecretsV1
Secrets
SecretTombstoneV1
Name
SharedEndpointRegionV1
SignalPromotionResponseV1
Success
SignSSHCertificateRequestV1
Public Key
Optionalreplica_id?: string | nullReplica Id
SignSSHCertificateResponseV1
Jwt
Proxy Address
Ssh Cert Expires At Format: date-time
Ssh Certificate
SortOrderV1
StopTrainingJobRequestV1
StopTrainingJobResponseV1
StorageMetricsV1
Usage Bytes
Utilization
SupportedModelV1
Max Context Length
Model Name
Supports Vision Language
SyncDeploymentPatchesRequestV1
SyncDeploymentPatchesResponseV1
Needs Full Deploy Reason
TeamV1
Created At Format: date-time
Default
Id
Name
TeamsV1
Teams
TeamTrainingGpuCapacityItemV1
Baseline
Dedicated Usage Count
Gpu Type
Limit
Spot Usage Count
Team Id
Team Name
Usage Count
TerminateReplicaResponseV1
Success
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>``.
TrainingGpuCapacityItemV1
Baseline
Dedicated Usage Count
Gpu Type
Limit
Spot Usage Count
Usage Count
TrainingItemV1
Optionaldaily?: components["schemas"]["DailyTrainingUsage"][]Daily
Minutes
Subtotal
TrainingJobV1
Created At Format: date-time
Current Status
Error Message
Id
Name
Node Count
Priority
Training Project Id
Updated At Format: date-time
TrainingJobCheckpointV1
Base Model
Checkpoint Id
Checkpoint Type
Created At Format: date-time
Lora Adapter Config
Size Bytes
Sync Status
Training Job Id
TrainingJobMetricV1
Timestamp Format: date-time
Value
TrainingJobMetricsV1
Cpu Memory Usage Bytes
Cpu Usage
Gpu Memory Usage Bytes
Gpu Utilization
TrainingJobNodeMetricsV1
Node Id
TrainingJobTombstoneV1
Deleted
Id
Training Project Id
TrainingProjectV1
Created At Format: date-time
Id
Name
Team Name
Updated At Format: date-time
TrainingProjectSummaryV1
Id
Name
TrainingProjectTombstoneV1
Deleted
Id
TrainingUsageV1
Optionalbreakdown?: components["schemas"]["TrainingItem"][]Breakdown
Credits Used
Minutes
Subtotal
Total
TrainingWeightAuthV1
Optionalauth_secret_name?: string | nullAuth Secret Name
Optionalaws_assume_role_arn?: string | nullAws Assume Role Arn
Optionalaws_assume_role_region?: string | nullAws Assume Role Region
Optionalaws_oidc_region?: string | nullAws Oidc Region
Optionalaws_oidc_role_arn?: string | nullAws Oidc Role Arn
Optionalgcp_oidc_service_account?: string | nullGcp Oidc Service Account
Optionalgcp_oidc_workload_id_provider?: string | nullGcp Oidc Workload Id Provider
TrussUserEnv
Optionalgit_info?: components["schemas"]["GitInfo"] | nullOptionalis_frontend_deployment?: booleanIs Frontend Deployment
Optionalis_library_deployment?: booleanIs Library Deployment
Optionalmypy_version?: string | nullMypy Version
Optionalpydantic_version?: string | nullPydantic Version
Optionalpython_version?: string | nullPython Version
Optionaltruss_client_version?: string | nullTruss Client Version
TTSBenchmarkMetricsV1
Optionalcost_per_audio_minute_usd?: number | nullCost Per Audio Minute Usd
Optionalmax_concurrent_streams_at_rtf1?: number | nullMax Concurrent Streams At Rtf1
Optionalttft_ms_p50?: number | nullTtft Ms P50
Optionalttft_ms_p50_at_max_concurrency?: number | nullTtft Ms P50 At Max Concurrency
UpdateAutoscalingScheduleSettingsV1
Optionaldelete_schedules?: string[]Delete Schedules
Optionalschedules?: (Schedules
Optionaltimezone?: string | nullTimezone
UpdateAutoscalingSettingsV1
Optionalautoscaling_window?: number | nullAutoscaling Window
Optionalconcurrency_target?: number | nullConcurrency Target
Optionalmax_replica?: number | nullMax Replica
Optionalmax_scale_down_rate?: number | nullMax Scale Down Rate
Optionalmin_replica?: number | nullMin Replica
Optionalscale_down_delay?: number | nullScale Down Delay
Optionaltarget_in_flight_tokens?: number | nullTarget In Flight Tokens
Optionaltarget_utilization_percentage?: number | nullTarget Utilization Percentage
UpdateAutoscalingSettingsResponseV1
Message
UpdateAutoscalingSettingsStatusV1
UpdateChainEnvironmentRequestV1
Optionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | nullUpdateChainEnvironmentResponseV1
Ok
UpdateChainletEnvironmentAutoscalingSettingsRequestV1
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"
}
]
UpdateChainletEnvironmentInstanceTypeRequestV1
Updates
UpdateChainletEnvironmentInstanceTypeResponseV1
Chainlet Environment Settings
Requires Redeployment
UpdateDeploymentRequestV1
Optionalname?: string | nullName
UpdateEndpointRequestV1
Optionaltargets?: components["schemas"]["EndpointTargetRequest"][] | nullTargets
UpdateEnvironmentGroupManageAccessV1
Is Restricted
Optionaluser_ids?: string[]User Ids
UpdateEnvironmentGroupRequestV1
Optionalmanage_access?: components["schemas"]["UpdateEnvironmentGroupManageAccess"] | nullUpdateEnvironmentRequestV1
Optionalautoscaling_schedule_settings?: components["schemas"]["UpdateAutoscalingScheduleSettings"] | nullPartial 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"
* }
Optionalautoscaling_settings?: components["schemas"]["UpdateAutoscalingSettings"] | nullOptionalpromotion_settings?: components["schemas"]["UpdatePromotionSettings"] | nullOptionalrequest_backpressure_settings?: components["schemas"]["UpdateRequestBackpressureSettings"] | nullUpdateEnvironmentResponseV1
Message
UpdateGroupMetadataV1
Optionalname?: string | nullName
UpdateGroupRequestV1
Optionalmetadata?: components["schemas"]["UpdateGroupMetadata"] | nullOptionalmodels?: components["schemas"]["ModelConfig"][] | nullModels
UpdateLibraryListingRequestV1
Optionaldisplay_name?: string | nullDisplay Name
Optionalis_public?: boolean | nullIs Public
Optionalmetadata?: components["schemas"]["LibraryListingMetadata"] | nullOptionaltrending?: boolean | nullTrending
UpdateLibraryListingVersionRequestV1
Optionalallow_truss_download?: boolean | nullAllow Truss Download
Optionalbenchmark?: components["schemas"]["BenchmarkSnapshot"] | nullOptionalis_live?: boolean | nullIs Live
UpdatePromotionSettingsV1
Optionalpromotion_cleanup_strategy?: components["schemas"]["PromotionCleanupStrategy"] | nullOptionalramp_up_duration_seconds?: number | nullRamp Up Duration Seconds
Optionalramp_up_while_promoting?: boolean | nullRamp Up While Promoting
Optionalredeploy_on_promotion?: boolean | nullRedeploy On Promotion
Optionalrolling_deploy?: boolean | nullRolling Deploy
Optionalrolling_deploy_config?: components["schemas"]["UpdateRollingDeployConfig"] | nullUpdateRequestBackpressureSettingsV1
Optionalpolicy?: components["schemas"]["RequestBackpressurePolicy"] | nullUpdateRollingDeployConfigV1
Optionalmax_surge_percent?: number | nullMax Surge Percent
Optionalmax_unavailable_percent?: number | nullMax Unavailable Percent
Optionalreplica_overhead_percent?: number | nullReplica Overhead Percent
Optionalrolling_deploy_strategy?: components["schemas"]["RollingDeployStrategy"] | nullOptionalstabilization_time_seconds?: number | nullStabilization Time Seconds
UpdateTrainingJobRequestV1
Optionalavailability_model?: components["schemas"]["V1AvailabilityModel"] | nullNew 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.
Optionalpriority?: number | nullPriority
UpdateTrainingJobResponseV1
UpsertSecretRequestV1
Name
Value
UpsertTrainingProjectV1
Name
UpsertTrainingProjectRequestV1
UpsertTrainingProjectResponseV1
UsageDimensionV1
UsageLimitV1
Threshold
UsageLimitUnitV1
UsageSummaryV1
UserV1
UserInfoV1
Name
User Id
Workspace Name
UsersResponseV1
Items
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
V1InteractiveSessionProvider
V1InteractiveSessionTrigger
ValidateLoopsCheckpointRequestV1
Checkpoint Path
ValidateLoopsCheckpointResponseV1
VertexTargetConfigV1
Location
Project Id
VolumeV1
Name
Namespace
Sequence
Tag Count
Tags
Updated At Format: date-time
Version Ref
Versions Alive
Versions Tombstoned
Versions Untagged
VolumeTagV1
Digest
Name
VolumeTokenScopeV1
VolumeVersionV1
Created At Format: date-time
Delete After
Digest
Is Head
Lifecycle
Namespace
Sequence
Tags
Tombstoned At
Total Size Bytes
Version Ref
Volume
VolumeVersionDetailV1
Created At Format: date-time
Delete After
Digest
Entry Count
Is Head
Lifecycle
Namespace
Sequence
Tags
Tombstoned At
Total Size Bytes
Version Ref
Volume
Volume Sequence
VolumeVersionSummaryV1
Created At Format: date-time
Digest
Total Size Bytes
This file was auto-generated by openapi-typescript. Do not make direct changes to the file.