Muse Wonder API access: Meta vs OpenRouter setup guide

Choose the provider before copying a model ID

Editorial synthesis · Cited sources· Last verified 2026-10-14

Meta and OpenRouter manage separate accounts, API keys, credits and billing. The model names and base URLs differ. A Meta key is not an OpenRouter key, even when the underlying model family is the same.

Meta’s official guide demonstrates the Responses API. The OpenRouter example here uses Chat Completions. Match the endpoint, request shape and model ID to the provider you actually selected.

Run a small, server-side request first

Editorial synthesis · Cited sources· Last verified 2026-10-14

Create a project or account with the selected provider, confirm billing and regional eligibility, then create a key in that provider’s dashboard. Store it as a server environment variable and install the OpenAI Python package for the examples below.

Send a short prompt before connecting tools, long histories or autonomous loops. Inspect returned usage and your provider’s billing page before expanding the workload. This guide never asks you to paste a key into this site.

Troubleshoot the boundary that failed

Editorial synthesis · Cited sources· Last verified 2026-10-14

For authentication errors, confirm the key belongs to the base URL you are calling. For model-not-found errors, check the provider-specific model ID and your account’s access. Increasing reasoning effort does not select Wonder Full.

For rate limits, respect Retry-After and use bounded backoff. For a schema error, check whether your client is sending a Responses or Chat Completions body. OpenRouter routing and provider policies can differ from direct Meta access.

Two providers, two complete examples

import os
from openai import OpenAI

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

response = client.responses.create(
    model="muse-wonder-1.0",
    input="Explain this codebase's architecture.",
)
print(response.output_text)

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key=os.environ["OPENROUTER_API_KEY"],
)
response = client.chat.completions.create(
    model="meta/muse-wonder",
    messages=[{"role": "user", "content": "Explain this codebase's architecture."}],
)
print(response.choices[0].message.content)