Choose an API

If you are building a new LLM integration, start with Responses API. Use the other APIs when you need embeddings, audio, moderation, image generation, or when you need to keep an existing client format.

​

Comparison

​

Quick choices

1. New text, multimodal, tool, or agent flows: use Responses API.
2. Retrieval, ranking, or semantic search: use Embeddings API.
3. TTS, transcription, or translation: use Audio API.
4. Text or image safety checks: use Moderations API.
5. Direct image generation or image editing: use Images API.
6. Existing OpenAI messages[] integration: use Chat Completions API.
7. Existing Anthropic-style integration: use Messages API.

​

Decision Shortcuts

​

Compatibility Layers

Use a compatibility API only when keeping the existing client format matters more than starting from the cleanest default.

• Chat Completions API keeps the OpenAI chat request format.
• Messages API keeps the Anthropic Messages request format.

Use them when you already have those clients, SDK abstractions, or agent tools in production. If you are starting from scratch, Responses API is usually the simpler choice.

​

Need Exact Fields?

Use the generated API Reference for endpoint contracts, request fields, and response schemas.

​

Reference Links

• Create response
• Create embeddings
• Create speech
• Create moderation
• Generate images
• Create chat completion
• Create message