Chat Completions
POST /v1/chat/completions is the most portable endpoint. It can call supported
Claude, GPT, Gemini, and Grok models by id.
Responses
POST /v1/responses follows OpenAI’s newer Responses shape and serves GPT models.
Use it for Codex-style GPT workflows. For Claude, Gemini, or Grok, use Chat Completions
unless your tool explicitly requires a different protocol.
POST /v1/responses/compact is available for clients that call the Responses
compaction path, including Codex-style context compaction flows.
Models
UseGET /v1/models for an OpenAI-compatible model list. For the human-readable
catalog, see Supported Models.