Skip to main content
The chat completions API generates a model response from a list of messages. It follows the OpenAI Chat Completions API, and you can use it with an OpenAI-compatible client or SDK. Which features and models are available depends on the model and on your CDF project.
Chat completions are in the alpha (20230101-alpha) API reference only. The stable and beta references do not include POST /ai/openai/chat/completions.

​
Rate limits

Requests are rate limited. When a limit is exceeded, the API returns HTTP 429 Too Many Requests. Retry with exponential backoff and jitter.
Last modified on October 6, 2026