Sign in
Batch

Create batch

Creates and executes a batch from an uploaded file of requests

post/batches

Request body

input_file_idstring required

The ID of an uploaded file that contains requests for the new batch.

See upload file for how to upload a file.

Your input file must be formatted as a JSONL file, and must be uploaded with the purpose batch. The file can contain up to 50,000 requests, and can be up to 200 MB in size.

endpoint'/v1/responses' | '/v1/chat/completions' | '/v1/embeddings' | '/v1/completions' | '/v1/moderations' | '/v1/images/generations' | '/v1/images/edits' | '/v1/videos' required

The endpoint to be used for all requests in the batch. Currently /v1/responses, /v1/chat/completions, /v1/embeddings, /v1/completions, /v1/moderations, /v1/images/generations, /v1/images/edits, and /v1/videos are supported. Note that /v1/embeddings batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch.

completion_window'24h' required

The time frame within which the batch should be processed. Currently only 24h is supported.

metadataMetadata nullable

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Response

Batch created successfully.

idstring required
object'batch' required

The object type, which is always batch.

endpointstring required

The OpenAI API endpoint used by the batch.

modelstring

Model ID used to process the batch, like gpt-6-astra. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

input_file_idstring required

The ID of the input file for the batch.

completion_windowstring required

The time frame within which the batch should be processed.

status'validating' | 'failed' | 'in_progress' | 'finalizing' | 'completed' | 'expired' | 'cancelling' | 'cancelled' required

The current status of the batch.

output_file_idstring

The ID of the file containing the outputs of successfully executed requests.

error_file_idstring

The ID of the file containing the outputs of requests with errors.

created_atinteger required

The Unix timestamp (in seconds) for when the batch was created.

in_progress_atinteger

The Unix timestamp (in seconds) for when the batch started processing.

expires_atinteger

The Unix timestamp (in seconds) for when the batch will expire.

finalizing_atinteger

The Unix timestamp (in seconds) for when the batch started finalizing.

completed_atinteger

The Unix timestamp (in seconds) for when the batch was completed.

failed_atinteger

The Unix timestamp (in seconds) for when the batch failed.

expired_atinteger

The Unix timestamp (in seconds) for when the batch expired.

cancelling_atinteger

The Unix timestamp (in seconds) for when the batch started cancelling.

cancelled_atinteger

The Unix timestamp (in seconds) for when the batch was cancelled.

metadataMetadata nullable

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

Changes

Changed in 3 of the 163 revisions of this API.413

  • b6ca60f934e84See the full diff
    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

    • ○

      added the non-success response with the status

      response-non-success-status-added

  • 74cbcf73838f48See the full diff
    • ▲

      the request property became not nullable

      request-property-became-not-nullable

    • ▲

      response property errors/data/items/line list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property errors/data/items/param list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ▲

      response property metadata list-of-types was widened by adding types null to media type application/json of response 200

      response-property-list-of-types-widened

    • ○

      added the new optional request property

      new-optional-request-property

    • ○

      added the new /v1/images/edits enum value to the request property

      request-property-enum-value-added

    • ○

      added the new /v1/images/generations enum value to the request property

      request-property-enum-value-added

    • ○

      added the new /v1/moderations enum value to the request property

      request-property-enum-value-added

    • ○

      added the new /v1/videos enum value to the request property

      request-property-enum-value-added

    • ○

      request property list-of-types was widened by adding types null to media type application/json

      request-property-list-of-types-widened

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    • ○

      added the optional property to the response with the status

      response-optional-property-added

    This revision also has 40 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog

  • 41844462b8731See the full diff
    • ○

      added the new /v1/responses enum value to the request property

      request-property-enum-value-added