OpenAI Batch API

The Batch API enables asynchronous processing of requests with 50% cost discount, higher rate limits, and completion within 24 hours. It supports /v1/responses, /v1/chat/completions, /v1/embeddings, /v1/completions, and /v1/moderations endpoints. A single batch may include up to 50,000 requests with a batch input file size up to 200 MB.

API entry from apis.yml

apis.yml Raw ↑
aid: openai:openai-batch-api
name: OpenAI Batch API
tags:
- Async
- Batch
score: 100
baseURL: https://api.openai.com
humanURL: https://platform.openai.com/docs/api-reference/batch
properties:
- url: https://platform.openai.com/docs/api-reference/batch
  type: Documentation
- url: https://platform.openai.com/docs/guides/batch
  type: Documentation
description: The Batch API enables asynchronous processing of requests with 50% cost discount, higher
  rate limits, and completion within 24 hours. It supports /v1/responses, /v1/chat/completions, /v1/embeddings,
  /v1/completions, and /v1/moderations endpoints. A single batch may include up to 50,000 requests with
  a batch input file size up to 200 MB.