Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation
Theme

Suggested
Overview Models Agents Tools Audio & voice Production API reference

Fine Tuning

Fine TuningAlpha

Fine TuningAlphaGraders

Manage fine-tuning jobs to tailor a model to your specific training data.

Run grader
fine_tuning.alpha.graders.run(**kwargs) -> GraderRunResponse
POST
/fine_tuning/alpha/graders/run
Validate grader
fine_tuning.alpha.graders.validate(**kwargs) -> GraderValidateResponse
POST
/fine_tuning/alpha/graders/validate
Models
class GraderRunResponse: …
class GraderValidateResponse: …

Fine TuningCheckpoints

Fine TuningCheckpointsPermissions

Manage fine-tuning jobs to tailor a model to your specific training data.

Create checkpoint permissions
fine_tuning.checkpoints.permissions.create(fine_tuned_model_checkpoint, **kwargs) -> SyncPage[PermissionCreateResponse]
POST
/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions
Delete checkpoint permission
fine_tuning.checkpoints.permissions.delete(permission_id, **kwargs) -> PermissionDeleteResponse
DELETE
/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}
List checkpoint permissions
fine_tuning.checkpoints.permissions.list(fine_tuned_model_checkpoint, **kwargs) -> SyncConversationCursorPage[PermissionListResponse]
GET
/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions
List checkpoint permissions
Deprecated
fine_tuning.checkpoints.permissions.retrieve(fine_tuned_model_checkpoint, **kwargs) -> PermissionRetrieveResponse
GET
/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions
Models
class PermissionCreateResponse: …

The checkpoint.permission object represents a permission for a fine-tuned model checkpoint.

class PermissionDeleteResponse: …
class PermissionListResponse: …

The checkpoint.permission object represents a permission for a fine-tuned model checkpoint.

class PermissionRetrieveResponse: …

Fine TuningJobs

Manage fine-tuning jobs to tailor a model to your specific training data.

Cancel fine-tuning
fine_tuning.jobs.cancel(fine_tuning_job_id) -> FineTuningJob
POST
/fine_tuning/jobs/{fine_tuning_job_id}/cancel
Create fine-tuning job
fine_tuning.jobs.create(**kwargs) -> FineTuningJob
POST
/fine_tuning/jobs
List fine-tuning jobs
fine_tuning.jobs.list(**kwargs) -> SyncCursorPage[FineTuningJob]
GET
/fine_tuning/jobs
List fine-tuning events
fine_tuning.jobs.list_events(fine_tuning_job_id, **kwargs) -> SyncCursorPage[FineTuningJobEvent]
GET
/fine_tuning/jobs/{fine_tuning_job_id}/events
Pause fine-tuning
fine_tuning.jobs.pause(fine_tuning_job_id) -> FineTuningJob
POST
/fine_tuning/jobs/{fine_tuning_job_id}/pause
Resume fine-tuning
fine_tuning.jobs.resume(fine_tuning_job_id) -> FineTuningJob
POST
/fine_tuning/jobs/{fine_tuning_job_id}/resume
Retrieve fine-tuning job
fine_tuning.jobs.retrieve(fine_tuning_job_id) -> FineTuningJob
GET
/fine_tuning/jobs/{fine_tuning_job_id}
Models
class FineTuningJob: …

The fine_tuning.job object represents a fine-tuning job that has been created through the API.

class FineTuningJobEvent: …

Fine-tuning job event object

class FineTuningJobWandbIntegration: …

The settings for your integration with Weights and Biases. This payload specifies the project that metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags to your run, and set a default entity (team, username, etc) to be associated with your run.

class FineTuningJobWandbIntegrationObject: …

Fine TuningJobsCheckpoints

Manage fine-tuning jobs to tailor a model to your specific training data.

List fine-tuning checkpoints
fine_tuning.jobs.checkpoints.list(fine_tuning_job_id, **kwargs) -> SyncCursorPage[FineTuningJobCheckpoint]
GET
/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints
Models
class FineTuningJobCheckpoint: …

The fine_tuning.job.checkpoint object represents a model checkpoint for a fine-tuning job that is ready to use.

Fine TuningMethods

Models
class DpoHyperparameters: …

The hyperparameters used for the DPO fine-tuning job.

class DpoMethod: …

Configuration for the DPO fine-tuning method.

class ReinforcementHyperparameters: …

The hyperparameters used for the reinforcement fine-tuning job.

class ReinforcementMethod: …

Configuration for the reinforcement fine-tuning method.

class SupervisedHyperparameters: …

The hyperparameters used for the fine-tuning job.

class SupervisedMethod: …

Configuration for the supervised fine-tuning method.