Chat Completions

Request

POST {BASE_URL}/v1/chat/completions

This endpoint uses an OpenAI-compatible request body. Common fields include model, messages, temperature, max_tokens, and stream.

Non-streaming example

curl

curl -sS "${BASE_URL}/v1/chat/completions" \
  -H "Authorization: Bearer ${API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "messages": [
      {
        "role": "system",
        "content": "You are a concise technical assistant."
      },
      {
        "role": "user",
        "content": "Explain asynchronous billing."
      }
    ],
    "temperature": 0.3,
    "max_tokens": 512
  }'

Python SDK

response = client.chat.completions.create(
    model="gpt-4.1",
    messages=[
        {"role": "system", "content": "You are a concise technical assistant."},
        {"role": "user", "content": "Explain asynchronous billing."},
    ],
    temperature=0.3,
    max_tokens=512,
)

print(response.choices[0].message.content)

Success response

{
  "id": "chatcmpl_xxx",
  "object": "chat.completion",
  "created": 1770000000,
  "model": "gpt-4.1",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Asynchronous billing means..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 42,
    "total_tokens": 66
  }
}