A valid request URL is required to generate request examples
{ "id": "<string>", "object": "batch", "endpoint": "<string>", "errors": { "object": "list", "data": [ { "code": "<string>", "message": "<string>", "param": "<string>", "line": 123 } ] }, "input_file_id": "<string>", "completion_window": "<string>", "status": "validating", "output_file_id": "<string>", "error_file_id": "<string>", "created_at": 123, "in_progress_at": 123, "expires_at": 123, "finalizing_at": 123, "completed_at": 123, "failed_at": 123, "expired_at": 123, "cancelling_at": 123, "cancelled_at": 123, "request_counts": { "total": 123, "completed": 123, "failed": 123 }, "metadata": {} }
Creates a batch of API requests for asynchronous processing.
API key passed as a Bearer token.
ID of the uploaded JSONL input file.
Target endpoint (e.g. /v1/chat/completions or /v1/embeddings).
/v1/chat/completions
/v1/embeddings
Completion window (e.g. 24h).
24h
Optional key-value metadata.
Show child attributes
Created batch object
"batch"
validating
in_progress
completed
failed
expired
cancelling
cancelled
Was this page helpful?