Chat Completions
Creates a model response for a given chat conversation.
POST /v1/chat/completions
Request parameters
| Param | Type | Required | Description |
|---|---|---|---|
model | string | yes | Model name, e.g. example-chat. |
messages | array | yes | Messages with role and content. |
temperature | number | no | Sampling temperature 0–2. Default 1.0. |
stream | boolean | no | Stream the response. Default false. |
Request example
- curl
- Python
- Node.js
curl https://api.example.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-d '{"model":"example-chat","messages":[{"role":"user","content":"hi"}]}'
resp = client.chat.completions.create(
model="example-chat",
messages=[{"role": "user", "content": "hi"}],
)
const resp = await client.chat.completions.create({
model: "example-chat",
messages: [{ role: "user", content: "hi" }],
});
Response example
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"choices": [{"index": 0, "message": {"role": "assistant", "content": "Hi!"}, "finish_reason": "stop"}],
"usage": {"prompt_tokens": 5, "completion_tokens": 2, "total_tokens": 7}
}