Skip to content

Glossary: Running Open Models Locally

Chat Completions API

Also written: /v1/chat/completions, client.chat.completions.create

OpenAI's standard request format for sending a list of messages and getting a reply. Ollama, llama-server and LM Studio all support it, so one client can talk to any of them.

Where the book teaches it

Related terms

OpenAI-compatible endpointResponses API