Guides
Chat completions
Our primary endpoint — assemble messages[], set model to a provider-scoped id (e.g. openai/gpt-4o), tune decoding, and optionally stream SSE.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
| model | string | Required | Provider-scoped model id (e.g. openai/gpt-4o, anthropic/claude-3-5-sonnet). Use GET /v1/models or the Models page to list all ids. |
| messages | array | Required | Array of message objects with role and content fields |
| max_tokens | integer | Optional | Maximum tokens to generate. Defaults to model maximum. |
| temperature | number | Optional | Sampling temperature between 0 and 2. Higher = more random. |
| top_p | number | Optional | Nucleus sampling probability mass. Between 0 and 1. |
| stream | boolean | Optional | If true, stream partial deltas as Server-Sent Events. |
| stop | string | array | Optional | Sequences where the API will stop generating tokens. |
OpenAI SDK mode + cURL
…cURL:
…Sample JSON
……Endpoint reference: POST /v1/chat/completions