Skip to content

OpenAI-Compatible API

Use this for Hermes, Cherry Studio, curl, OpenAI Python/Node SDK, and any other OpenAI-compatible client.

Base URL

Different clients expect different base URL formats. If one does not work, try the other.

txt
https://codex-easy.ai
https://codex-easy.ai/v1

API key

Use your CE API key as the OpenAI API key.

txt
<your-ce-api-key>

Common request paths

Common endpoints:

txt
/v1/models
/v1/responses
/v1/chat/completions
/v1/images/*

/v1/images/* only works for image-generation groups.

Notes

Caching is optimized for Codex and OpenCode. Third-party clients may experience lower cache hit rates, so test cache behavior with your own workload.

When calling the API directly, pass session_id and prompt_cache_key to enable cache hits. You can observe how the Codex client constructs these fields to guide your own implementation.

OpenAI API reference: platform.openai.com/docs/api-reference