Create a Chat Completion
Generate a conversational response with the OpenAI-compatible Chat Completions API.
Create a model response from a list of messages. Existing OpenAI-compatible clients can use this endpoint by changing the base URL and API key.
POST
/openai/v1/chat/completionsRequest Body
| Field | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model identifier available to the API key's tenant. |
messages | array | Yes | Ordered conversation messages with role and content. |
stream | boolean | No | Stream incremental response events when true. |
temperature | number | No | Sampling temperature supported by the selected model. |
Response
The response preserves the OpenAI-compatible chat.completion shape, including choices, the assistant message, and the finish reason.
Compatibility Alias
The gateway still accepts /v1/chat/completions for compatible existing clients. Use /openai/v1/chat/completions for new integrations so the protocol namespace is explicit.