Hacker News Reader

Sorry, to clarify: OpenAI has an specification for their API endpoints that most vendors are compatible with or have adopted wholesale.

So, if your model inference server understands the REST API spec that OpenAI created way back, you can use a huge range of libraries that in theory only "work" with OpenAI.

View on HN

> OpenAI has an specification for their API endpoints that most vendors are compatible with or have adopted wholesale

Worth clarifying that what the ecosystem/vendors have adopted is the "ChatCompletion" endpoint, which most models are under. But newer models (like codex) are only available under the Responses API, which the ecosystem/vendors haven't adopted as widely, AFAIK.

Reply on news.ycombinator.com