---
id: "meta/muse-wonder"
also: ["meta/muse-wonder-20261012"]
card_usd_per_m: "4.0 in, 20.0 out, at meta"
cheapest_list_usd_per_m: "4.0 in, 20.0 out, at google-vertex/global on openrouter"
cheapest_effective_usd_per_m: "0.6407 in, 20.0 out, at meta on openrouter"
context: 1048576
max_output: 943718
input: ["text", "image", "video", "file", "audio"]
output: ["text"]
released: "2026-10-12"
reasoning: ["max", "xhigh", "high", "medium", "low", "minimal"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p"]
endpoints: 2
gateways: "openrouter (2)"
no_training: 2
trains: 0
retains_prompts: 1
intelligence: 43.6000
---
# Meta: Muse Wonder

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...