Chat completions

You're Claude Code, working in my repository.

Task
Call POST /v1/chat/completions from my app with the request shape this reference documents (model and messages, plus max_completion_tokens, reasoning_effort, response_format and tools as needed) and read choices[0].message and usage from the reply.

Read this first
Meta's docs page "Chat completions" as Markdown: https://dev.meta.ai/docs/api-reference/chat-completions.md
It's the source of truth for request and response shapes. The same page for people: https://dev.meta.ai/docs/api-reference/chat-completions

Setup
- Base URL: https://api.meta.ai/v1
- Auth: send Authorization: Bearer $MODEL_API_KEY, reading MODEL_API_KEY from the environment. Never hard-code, print or commit the key.
- Model: muse-spark-1.3-contributor (Contributor mode: Meta may use what you send to train future models; drop -contributor for Standard mode)
- Python: the OpenAI SDK (pip install openai) with base_url="https://api.meta.ai/v1" and api_key=os.environ["MODEL_API_KEY"] works, or plain requests.

Facts to get right
- Reasoning isn't carried across turns on this endpoint; use the Responses API for agentic, multi-step work.
- The reply is CreateChatCompletionResponse: one choice, choices[0].message.content (or tool_calls), finish_reason stop, length or tool_calls, usage prompt_tokens and completion_tokens.
- A stream sends chat.completion.chunk events with choices[0].delta; stream_options {"include_usage": true} adds usage on the last chunk; it ends with [DONE].
- n must be 1; stop, logprobs, modalities and audio are 400s on Muse Spark.

Starter code (Python)
import os

from openai import OpenAI

client = OpenAI(base_url="https://api.meta.ai/v1", api_key=os.environ["MODEL_API_KEY"])
MODEL = "muse-spark-1.3-contributor"

response = client.chat.completions.create(
    model=MODEL,
    messages=[{"role": "user", "content": "What are three differences between TCP and UDP?"}],
    max_completion_tokens=1500,
)
print(response.choices[0].message.content, response.choices[0].finish_reason, response.usage)

Done when
- A call prints choices[0].message.content and usage; a streamed call prints deltas and the final usage.
- The key comes from MODEL_API_KEY and never appears in code, logs or commits.
- API errors (4xx, 429) surface their message instead of failing silently.