cURL
curl --request GET \ --url http://localhost:8080/v1/batches \ --header 'x-model-provider: <x-model-provider>'
{ "object": "<string>", "data": [ { "id": "<string>", "object": "<string>", "endpoint": "<string>", "input_file_id": "<string>", "completion_window": "<string>", "status": "validating", "request_counts": { "total": 123, "completed": 123, "failed": 123 }, "created_at": 123, "expires_at": 123, "in_progress_at": 123, "completed_at": 123, "failed_at": 123, "output_file_id": "<string>", "error_file_id": "<string>", "extra_fields": "<unknown>" } ], "has_more": true, "first_id": "<string>", "last_id": "<string>", "extra_fields": "<unknown>" }
Lists all batch jobs for the authenticated user.
The model provider to use (e.g., openai, anthropic, azure, bedrock, gemini)
Maximum number of batches to return
Cursor for pagination
List of batches
Show child attributes
validating
failed
in_progress
finalizing
completed
expired
cancelling
cancelled
Was this page helpful?