Generate an image

You're Claude Code, working in my repository.

Task
Add a generate_image function to my app that calls POST /v1/images/generations with muse-image-1.0 and a prompt, takes n, size and output_format, and writes each data[].b64_json to a file.

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

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-image-1.0
- 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
- model and prompt are required; n is 1 to 10 (default 1). size "WxH" sets only the aspect ratio, and beyond 16:1 is a 400.
- response_format b64_json (default) or url (a temporary signed link); output_format webp (default), png or jpeg.
- reasoning_strength high (default) or low (one pass, faster); temperature 0 to 2 tunes only planning; tool_enablement {enable_image_search, enable_web_search, enable_shell}, all on by default; user: an end-user id.
- OpenAI SDK: send reasoning_strength and tool_enablement in extra_body. moderation and unknown top-level fields are 400s.
- stream: true sends one image_generation.completed event with b64_json and usage. $0.01 per image.

Starter code (Python)
import base64
import os

from openai import OpenAI

client = OpenAI(base_url="https://api.meta.ai/v1", api_key=os.environ["MODEL_API_KEY"])


def generate_image(prompt, n=1, size=None, output_format="webp"):
    response = client.images.generate(
        model="muse-image-1.0",
        prompt=prompt,
        n=n,
        **({"size": size} if size else {}),
        output_format=output_format,
        extra_body={"reasoning_strength": "low"},
    )
    paths = []
    for i, image in enumerate(response.data):
        path = f"image-{i}.{output_format}"
        with open(path, "wb") as f:
            f.write(base64.b64decode(image.b64_json))
        paths.append(path)
    return paths


print(generate_image("a watercolor painting of a red fox sitting in a snowy pine forest, soft golden morning light", size="1536x1024"))

Done when
- generate_image("a red fox", n=1) writes one image file that opens.
- size 1536x1024 returns a landscape image, and output_format png writes PNG bytes.
- An invalid size or field prints Meta's 400 message with its param.
- 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.