Skip to main content
The Batch API processes hundreds, thousands, or up to 50,000 inference requests at a discounted rate within a 24-hour window. It’s the right choice when you don’t need a real-time response and want to avoid per-request rate limits.

Quickstart

Run your first batch end to end in curl and Python: upload, create, poll, download.

Objects & lifecycle

The File and Batch objects, the status lifecycle, and every endpoint.

JSONL format

Line schemas for input, output, and error files, plus validation rules.

Supported endpoints

The one endpoint a batch line can target, with its request and response body.

Errors

Every status and error-file code, with recovery guidance.

​
Quick facts

​
When to use the Batch API

Every endpoint also has an interactive playground under API Reference → Batch API.