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

Suggested
Overview Models Agents Tools Audio & voice Production API reference
API Reference

Fine Tuning

Fine TuningAlpha

Fine TuningAlphaGraders

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

Run grader
client.fineTuning.alpha.graders.run(GraderRunParams { grader, model_sample, item } body, RequestOptionsoptions?): GraderRunResponse { metadata, model_grader_token_usage_per_model, reward, sub_rewards }
POST/fine_tuning/alpha/graders/run
Validate grader
client.fineTuning.alpha.graders.validate(GraderValidateParams { grader } body, RequestOptionsoptions?): GraderValidateResponse { grader }
POST/fine_tuning/alpha/graders/validate
ModelsExpand Collapse
GraderRunResponse { metadata, model_grader_token_usage_per_model, reward, sub_rewards }
GraderValidateResponse { grader }

Fine TuningCheckpoints

Fine TuningCheckpointsPermissions

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

Create checkpoint permissions
client.fineTuning.checkpoints.permissions.create(stringfineTunedModelCheckpoint, PermissionCreateParams { project_ids } body, RequestOptionsoptions?): Page<PermissionCreateResponse { id, created_at, object, project_id } >
POST/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions
Delete checkpoint permission
client.fineTuning.checkpoints.permissions.delete(stringpermissionID, PermissionDeleteParams { fine_tuned_model_checkpoint } params, RequestOptionsoptions?): PermissionDeleteResponse { id, deleted, object }
DELETE/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}
List checkpoint permissions
client.fineTuning.checkpoints.permissions.list(stringfineTunedModelCheckpoint, PermissionListParams { after, limit, order, project_id } query?, RequestOptionsoptions?): ConversationCursorPage<PermissionListResponse { id, created_at, object, project_id } >
GET/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions
List checkpoint permissions
Deprecated
client.fineTuning.checkpoints.permissions.retrieve(stringfineTunedModelCheckpoint, PermissionRetrieveParams { after, limit, order, project_id } query?, RequestOptionsoptions?): PermissionRetrieveResponse { data, has_more, object, 2 more }
GET/fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions
ModelsExpand Collapse
PermissionCreateResponse { id, created_at, object, project_id }

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

PermissionDeleteResponse { id, deleted, object }
PermissionListResponse { id, created_at, object, project_id }

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

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
client.fineTuning.jobs.cancel(stringfineTuningJobID, RequestOptionsoptions?): FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs/{fine_tuning_job_id}/cancel
Create fine-tuning job
client.fineTuning.jobs.create(JobCreateParams { model, training_file, hyperparameters, 6 more } body, RequestOptionsoptions?): FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs
List fine-tuning jobs
client.fineTuning.jobs.list(JobListParams { after, limit, metadata } query?, RequestOptionsoptions?): CursorPage<FineTuningJob { id, created_at, error, 16 more } >
GET/fine_tuning/jobs
List fine-tuning events
client.fineTuning.jobs.listEvents(stringfineTuningJobID, JobListEventsParams { after, limit } query?, RequestOptionsoptions?): CursorPage<FineTuningJobEvent { id, created_at, level, 4 more } >
GET/fine_tuning/jobs/{fine_tuning_job_id}/events
Pause fine-tuning
client.fineTuning.jobs.pause(stringfineTuningJobID, RequestOptionsoptions?): FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs/{fine_tuning_job_id}/pause
Resume fine-tuning
client.fineTuning.jobs.resume(stringfineTuningJobID, RequestOptionsoptions?): FineTuningJob { id, created_at, error, 16 more }
POST/fine_tuning/jobs/{fine_tuning_job_id}/resume
Retrieve fine-tuning job
client.fineTuning.jobs.retrieve(stringfineTuningJobID, RequestOptionsoptions?): FineTuningJob { id, created_at, error, 16 more }
GET/fine_tuning/jobs/{fine_tuning_job_id}
ModelsExpand Collapse
FineTuningJob { id, created_at, error, 16 more }

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

FineTuningJobEvent { id, created_at, level, 4 more }

Fine-tuning job event object

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.

FineTuningJobWandbIntegrationObject { type, wandb }

Fine TuningJobsCheckpoints

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

List fine-tuning checkpoints
client.fineTuning.jobs.checkpoints.list(stringfineTuningJobID, CheckpointListParams { after, limit } query?, RequestOptionsoptions?): CursorPage<FineTuningJobCheckpoint { id, created_at, fine_tuned_model_checkpoint, 4 more } >
GET/fine_tuning/jobs/{fine_tuning_job_id}/checkpoints
ModelsExpand Collapse
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
DpoHyperparameters { batch_size, beta, learning_rate_multiplier, n_epochs }

The hyperparameters used for the DPO fine-tuning job.

DpoMethod { hyperparameters }

Configuration for the DPO fine-tuning method.

ReinforcementHyperparameters { batch_size, compute_multiplier, eval_interval, 4 more }

The hyperparameters used for the reinforcement fine-tuning job.

ReinforcementMethod { grader, hyperparameters }

Configuration for the reinforcement fine-tuning method.

SupervisedHyperparameters { batch_size, learning_rate_multiplier, n_epochs }

The hyperparameters used for the fine-tuning job.

SupervisedMethod { hyperparameters }

Configuration for the supervised fine-tuning method.