MCP / Models / Language models

Muse Wonder MCP: hard reasoning and coding with no API key

Meta Muse Wonder is the frontier Muse model for hard reasoning, coding and agents, with image input, function tools and a 1M-token context. Run it from Claude Code, Codex, Cursor or any MCP client through one FlyMy.AI MCP, or call its API.

No API key$4.00 / $20.00 per 1M tokensChat modelMetaCommercial use
Muse Wonder sample from the FlyMy.AI catalog

$ YOUR NEXT RUN

Claude CodeCodexCursorAny agent

Use Muse Wonder in your assistant

Paste this prompt into Claude Code, Codex, Cursor or any agent. It reads the guide and helps you connect.

Read https://flymy.ai/skill.md and https://flymy.ai/mcp/models/muse-wonder.md. Help me connect the FlyMy.AI MCP to this assistant, then run Muse Wonder (flymyai/muse-wonder) for this task: Ask Muse Wonder: plan the steps to migrate this API to a new version.
Open FlyMy.AIDownload brief

What Muse Wonder does

Send a prompt, or a chat history in messages with images as image_url parts, and get a text answer from a 1M-token context. reasoning_effort is low, medium, high, xhigh or max (medium by default), and reasoning tokens are billed as output; system_prompt and max_tokens (up to 131,072) work as usual, and private_mode keeps the prompt and answer out of FlyMy.AI storage and logs on synchronous calls. Call it with your FlyMy.AI key in two ways: the FlyMy.AI API, or the OpenAI-compatible Chat Completions endpoint, where it also calls your function tools and takes their results back. It answers in text only; use the image, video and audio models to create media.

Muse Wonder inputs

Every input of flymyai/muse-wonder as its live schema lists them. Returns output (string), finish_reason (string), service_tier (string), reasoning (string), stream_details (string).

InputType, values and default
# prompt
string required What to ask Muse Wonder
# messages
string optional Chat history as a JSON array of {role, content}; used instead of the prompt
# system_prompt
string optional Instructions for the whole chat
# reasoning_effort
string optional Allowed: low, medium, high, xhigh, max Default: medium How hard Muse Wonder thinks before answering
# max_tokens
integer optional Allowed: 1 to 131072 Most tokens to generate, reasoning included
# private_mode
boolean optional Default: false Keep the prompt and the answer out of FlyMyAI storage and logs (synchronous requests only)

Ask your agent

Requests to paste as they are, once the FlyMy.AI MCP is connected.

“Ask Muse Wonder: plan the steps to migrate this API to a new version.”runs flymyai/muse-wonder
“Explain this stack trace and suggest a fix with Muse Wonder.”runs flymyai/muse-wonder
“With Muse Wonder, turn these meeting notes into a list of action items with owners.”runs flymyai/muse-wonder

Muse Wonder price

$4.00 per 1M input tokens, $20.00 per 1M output tokens, cached input $0.20 per 1M. Cached input is $0.20 per 1M tokens. Billed to your FlyMy.AI balance; no seats, no subscription and no minimum.

Call Muse Wonder from code

The same model, from an agent or from your own code. Keys stay in your FlyMy.AI account.

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/muse-wonder",
  "input": {
    "prompt": "Explain in two sentences what an MCP server is."
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. Text models answer on the streaming route.

curl -X POST https://api.flymy.ai/api/v1/flymyai/muse-wonder/predict/stream/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Explain in two sentences what an MCP server is.'

With the OpenAI SDK

Muse Wonder also answers the OpenAI Chat Completions protocol.

from openai import OpenAI

client = OpenAI(base_url="https://api.flymy.ai/api/v1/flymyai/muse-wonder/openai/v1", api_key="YOUR_FLYMYAI_KEY")
reply = client.chat.completions.create(
    model="flymyai/muse-wonder",
    messages=[{"role": "user", "content": "Explain in two sentences what an MCP server is."}],
)
print(reply.choices[0].message.content)

Questions about Muse Wonder

Do I need a Meta API key for Muse Wonder?

No. Muse Wonder runs on FlyMy.AI's account, so you need no Meta key or plan: sign in to FlyMy.AI once and each run is billed to your FlyMy.AI balance.

How much does Muse Wonder cost?

$4.00 per 1M input tokens, $20.00 per 1M output tokens, cached input $0.20 per 1M. There is no subscription or minimum; the price comes from FlyMy.AI billing and was checked on 2026-11-18.

How do I use Muse Wonder in Claude Code, Codex or Cursor?

Add the FlyMy.AI MCP with one command and sign in, then ask in plain words, for example: "Ask Muse Wonder: plan the steps to migrate this API to a new version." Your agent reads the inputs with get_model_schema and runs flymyai/muse-wonder with run_model.

What does Muse Wonder need as input?

Muse Wonder requires prompt; it also takes 5 optional inputs, each listed on this page with its allowed values and default.

Can I call Muse Wonder from my own code?

Yes. Send form fields to https://api.flymy.ai/api/v1/flymyai/muse-wonder/predict/stream/ with your FlyMy.AI API key in the X-API-KEY header; it also answers the OpenAI Chat Completions protocol at https://api.flymy.ai/api/v1/flymyai/muse-wonder/openai/v1.

Go to the source

From the FlyMy.AI model catalog of 2026-11-18: inputs from the model's live schema, prices from FlyMy.AI billing. Requests are examples to paste, not recorded runs.