API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

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 { metadata, model_grader_token_usage_per_model, reward, sub_rewards }

POST/fine_tuning/alpha/graders/run

Validate grader

fine_tuning.alpha.graders.validate(**kwargs) -> GraderValidateResponse { grader }

POST/fine_tuning/alpha/graders/validate

ModelsExpand Collapse

class GraderRunResponse { metadata, model_grader_token_usage_per_model, reward, sub_rewards }

class GraderValidateResponse { grader }

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) -> Page<PermissionCreateResponse { id, created_at, object, project_id } >

POST/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions

Delete checkpoint permission

fine_tuning.checkpoints.permissions.delete(permission_id, **kwargs) -> PermissionDeleteResponse { id, deleted, object }

DELETE/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}

List checkpoint permissions

fine_tuning.checkpoints.permissions.list(fine_tuned_model_checkpoint, **kwargs) -> ConversationCursorPage<PermissionListResponse { id, created_at, object, project_id } >

GET/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions

List checkpoint permissions

Deprecated

fine_tuning.checkpoints.permissions.retrieve(fine_tuned_model_checkpoint, **kwargs) -> PermissionRetrieveResponse { data, has_more, object, 2 more }

GET/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions

ModelsExpand Collapse

class PermissionCreateResponse { id, created_at, object, project_id }

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

class PermissionDeleteResponse { id, deleted, object }

class PermissionListResponse { id, created_at, object, project_id }

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

class PermissionRetrieveResponse { data, has_more, object, 2 more }

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 { id, created_at, error, 16 more }

POST/fine_tuning/jobs/{fine_tuning_job_id}/cancel

Create fine-tuning job

fine_tuning.jobs.create(**kwargs) -> FineTuningJob { id, created_at, error, 16 more }

POST/fine_tuning/jobs

List fine-tuning jobs

fine_tuning.jobs.list(**kwargs) -> CursorPage<FineTuningJob { id, created_at, error, 16 more } >

GET/fine_tuning/jobs

List fine-tuning events

fine_tuning.jobs.list_events(fine_tuning_job_id, **kwargs) -> CursorPage<FineTuningJobEvent { id, created_at, level, 4 more } >

GET/fine_tuning/jobs/{fine_tuning_job_id}/events

Pause fine-tuning

fine_tuning.jobs.pause(fine_tuning_job_id) -> FineTuningJob { id, created_at, error, 16 more }

POST/fine_tuning/jobs/{fine_tuning_job_id}/pause

Resume fine-tuning

fine_tuning.jobs.resume(fine_tuning_job_id) -> FineTuningJob { id, created_at, error, 16 more }

POST/fine_tuning/jobs/{fine_tuning_job_id}/resume

Retrieve fine-tuning job

fine_tuning.jobs.retrieve(fine_tuning_job_id) -> FineTuningJob { id, created_at, error, 16 more }

GET/fine_tuning/jobs/{fine_tuning_job_id}

ModelsExpand Collapse

class FineTuningJob { id, created_at, error, 16 more }

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

class FineTuningJobEvent { id, created_at, level, 4 more }

Fine-tuning job event object

class FineTuningJobWandbIntegration { project, entity, name, tags }

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 { type, wandb }

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) -> CursorPage<FineTuningJobCheckpoint { id, created_at, fine_tuned_model_checkpoint, 4 more } >

GET/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints

ModelsExpand Collapse

class FineTuningJobCheckpoint { id, created_at, fine_tuned_model_checkpoint, 4 more }

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

Fine TuningMethods

ModelsExpand Collapse

class DpoHyperparameters { batch_size, beta, learning_rate_multiplier, n_epochs }

The hyperparameters used for the DPO fine-tuning job.

class DpoMethod { hyperparameters }

Configuration for the DPO fine-tuning method.

class ReinforcementHyperparameters { batch_size, compute_multiplier, eval_interval, 4 more }

The hyperparameters used for the reinforcement fine-tuning job.

class ReinforcementMethod { grader, hyperparameters }

Configuration for the reinforcement fine-tuning method.

class SupervisedHyperparameters { batch_size, learning_rate_multiplier, n_epochs }

The hyperparameters used for the fine-tuning job.

class SupervisedMethod { hyperparameters }

Configuration for the supervised fine-tuning method.