Create a chat completion

Generate a model response from a conversation supplied as a list of messages.

POST /chat/completions

Generate a chat completion.

Request body

Content Type: application/json

CreateChatCompletionRequest

Response

HTTP 200 — OK

Content Type: application/json

CreateChatCompletionResponse

Content Type: text/event-stream

CreateChatCompletionStreamResponse

python
import os
​
from openai import OpenAI
​
client = OpenAI(
    base_url="https://api.meta.ai/v1",
    api_key=os.environ["MODEL_API_KEY"],
)
​
response = client.chat.completions.create(
    model="muse-spark-1.3",
    messages=[
        {
            "role": "user",
            "content": "What are three differences between TCP and UDP?",
        },
    ],
)
​
print(response.model_dump_json(indent=2))

For usage examples, streaming, multi-turn conversations, and parameter guidance, see the Chat completion feature page.