Felo API PlatformFelo API Platform
Back to models
Metamessages

Muse Wonder API

Meta's frontier agent model with Active Memory and Active Focus, a roughly one-million-token context window, and multimodal input for long-running professional work.

Muse Wonder is the standard model in the frontier family Meta Superintelligence Labs (MSL) released in October 2026. It sits alongside the stronger Muse Wonder Full and is aimed squarely at personal and professional agent work.

Two mechanisms define it. Active Memory carries background from earlier conversations into later tasks and proactively recalls the relevant details, while Active Focus keeps the model pushing on hard problems: it tries alternatives, recovers from its own errors, and checks with the user before taking significant actions. The context window is about one million tokens, inputs can be text, images, video, or audio, and output is text.

That makes it a fit for long-running autonomous coding, large codebase changes and automated debugging, document-heavy agents in legal, finance, and healthcare (insurance claims, lease review, personal finance), plus cross-application automation and computer use. It is available through the Meta Model API on usage-based pricing with an OpenAI-compatible endpoint. Design-oriented output such as SVG illustration and short video editing is a weaker area.

Open Playground ↗Create API Key ↗Getting started →

Updated:

MODEL ID

muse-wonder
Context
1.049M
Max output
943.718K
Recommended API
messages
Input
text / image / video / file / audio
Output
text

Providers

1 providers

Compare API prices across providers. Select a provider to view all charges and conditions.

Provider · Pricing details
$4$20$0.2

What $10 buys

Input
2.5M tokens
Output
500K tokens

Estimated from current input and output prices, before discounts.

Reasoning

Default effort
medium
Always enabled
Yes
Available effort levels
max / xhigh / high / medium / low / minimal

Quick Start

Drop-in code to call this model with Felo API Platform compatible APIs. Start in the Playground when you want to test prompts before writing code.

Open PlaygroundCreate API Key
1

Get your API key

Create a key from your Felo API Platform account and set it as an environment variable.

export FELO_API_KEY="YOUR_API_KEY"
2

Make your first request

Use this model ID with the Felo API Platform endpoint. Optional request headers such as X-Request-Id can help troubleshooting.

muse-wonder

This model is reasoning-capable. If your selected protocol and model route expose reasoning controls, preserve the returned reasoning metadata when continuing a conversation.

const response = await fetch("https://openapi.felo.ai/api/v1/messages", {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.FELO_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
  "model": "muse-wonder",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}),
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());

Using third-party SDKs

Use compatible SDKs by setting baseURL to https://openapi.felo.ai/api/v1. Use the Anthropic-compatible base URL for Claude-style clients. https://openapi.felo.ai/api.

3

Enable streaming

Add stream: true to receive responses as server-sent events.

curl -N https://openapi.felo.ai/api/v1/messages \
  -H "Authorization: Bearer $FELO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "muse-wonder",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "stream": true
}'

Endpoint

Felo API Platform exposes compatible model-calling surfaces. Pick the surface your app or agent client already supports.

SurfaceMethodURL

Messages

Anthropic-compatible messages for Claude-style clients.

POST

https://openapi.felo.ai/api/v1/messages

Parameters

NameTypeDefaultDescription
modelstringmuse-wonderPublic model ID to call.
max_tokensinteger—Maximum generated tokens.
messagesarray—Conversation messages for Chat Completions.
include_reasoning———
reasoning———
reasoning_effort———
repetition_penalty———
response_formatobject—Request structured output when supported.
structured_outputs———
temperaturenumber—Controls response variety when supported.
tool_choicestring or object—Controls whether a tool should be called.
toolsarray—Tool calling definitions following compatible schema.
top_k———
top_p———

Frequently asked questions

What is Muse Wonder?

Muse Wonder is the standard model in the frontier family Meta Superintelligence Labs (MSL) released in October 2026. It sits alongside the stronger Muse Wonder Full and is aimed squarely at personal and professional agent work. Two mechanisms define it. Active Memory carries background from earlier conversations into later tasks and proactively recalls the relevant details, while Active Focus keeps the model pushing on hard problems: it tries alternatives, recovers from its own errors, and checks with the user before taking significant actions. The context window is about one million tokens, inputs can be text, images, video, or audio, and output is text. That makes it a fit for long-running autonomous coding, large codebase changes and automated debugging, document-heavy agents in legal, finance, and healthcare (insurance claims, lease review, personal finance), plus cross-application automation and computer use. It is available through the Meta Model API on usage-based pricing with an OpenAI-compatible endpoint. Design-oriented output such as SVG illustration and short video editing is a weaker area.

How is usage billed?

Your bill depends on the provider you use, its prices and your usage. Longer inputs or other conditions may have different prices.