Back to models
Meta
Muse Wonder
proprietaryReleased Oct 12, 2026
Meta's multimodal reasoning model for coding, computer use, and long-running personal and professional agents. Accepts text, images, audio, video, and documents with a 1,048,576-token context window and adjustable reasoning effort. Available through Meta Model API, Muse Code, and OpenRouter.
ChatText completionFunction callingVisionAudioCode generationReasoningtext · image · audio · video · code
Available from 2 providers
Cheapest
Meta AI
$4.00 / $20.00
Meta AI, OpenRouter
Providers (2)
Sorted by total cost (input + output per 1M tokens). Select a row to view provider details.
| Provider | Pricing (per 1M) | Rate limits | Regions | Health | Latency |
|---|---|---|---|---|---|
| In: $4.00Out: $20.00 | N/A RPM / N/A TPM | global | Healthy | 0ms |
| In: $4.00Out: $20.00 | N/A RPM / N/A TPM | us-east-1 | Healthy | 0ms |
Quick start
Use this model via Meta AI with an OpenAI-compatible SDK.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.meta.com/v1",
apiKey: process.env.META_API_KEY,
});
const response = await client.chat.completions.create({
model: "muse-wonder-1.0",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);Using Meta AI API · OpenAI-compatible SDK