meta/muse-wonder

模型发布 OpenRouter 模型 原文语言:中文

OpenRouter 于 2026-10-12 收录该模型(收录时间不等于模型正式发布日期);上下文:1,048,576 tokens;输入价:$4.0000/百万 tokens;输出价:$20.0000/百万 tokens;定位(来源描述):Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and…

全文

Meta: Muse Wonder

meta/muse-wonder

Compare

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 a 1M-token context window.

The model handles long-horizon work: it plans, delegates to sub-agents, calls tools in parallel, and recovers from errors, so multi-step tasks run to completion without step-by-step direction. It can also operate browsers and desktop and mobile applications, and works across many files in existing repositories to make and verify changes. Muse Wonder carries important context across conversations and retrieves the details relevant to the task at hand. And it's trained for Active Focus, so it works toward your goal even when a task gets challenging.

In Meta's testing, it performs well on complex engineering tasks, extended agentic sessions, and multi-file refactors to tackle developers' most demanding work.

Modalities

In / out price

$4 / $20per 1M

Context

1.0M

Released

Oct 12, 2026

Compare

Providers

Different companies host the same model. OpenRouter routes your request to one of them based on the routing mode you pick: Balanced (price + speed), Nitro (fastest), or Floor (cheapest).

Latency / throughput

$4.00$20.00$0.201.69s125 tok/s

99.92%

$4.00$20.00$0.202.70s91 tok/s

99.23%

ProviderInput / Output /M

Input $4.00 / Output $20.00

125 tok/s99.92% uptime

Input $4.00 / Output $20.00

91 tok/s99.23% uptime

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Weighted average

Input

$0.511/M tokens

Output

$20/M tokens

Muse Wonder — Price history

Price history

No effective price data for this selection

$0.491$20.0092.4%30.2%

$0.520$20.0091.6%69.8%

ProviderInput / Output /M

Token share

Effective in $0.491 / Effective out $20.00

Token share

30.2%

Effective in $0.520 / Effective out $20.00

Token share

69.8%

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Throughput

125tok/s

P50, best across providers

Latency

1.69s

P50, best provider

Reasoning effortLatency / throughput

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Uptime (3d)The model was reachable. Request routed to a provider.

100.00%

Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.

99.73%

Availability over the last 3 days

Last 72 hours

Availability 99.73%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.66%

Without Routing

99.30%

When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Meta: Muse Wonder (Artificial Analysis, Design Arena and Vals AI)

SourceBenchmarkScore

Artificial AnalysisMuse Wonder (Max) Intelligence Index43.6

Artificial AnalysisMuse Wonder (Max) HLE50.1%

Artificial AnalysisMuse Wonder (Max) AA-LCR80.7%

Artificial AnalysisMuse Wonder (Max) GDPval-AA63.5%

Artificial AnalysisMuse Wonder (Max) CritPt28.3%

Artificial AnalysisMuse Wonder (Max) SciCode60.3%

Artificial AnalysisMuse Wonder (Max) Terminal-Bench 4.052.0%

Artificial AnalysisMuse Wonder (Max) AA-Omniscience Accuracy38.0%

Artificial AnalysisMuse Wonder (Max) AA-Omniscience Non-Hallucination Rate79.1%

Design ArenaMuse Wonder (max) Agents Arena Blender3d Elo1149

Design ArenaMuse Wonder (max) Agents Arena Codetovideo Elo1199

Design ArenaMuse Wonder (max) Agents Arena Htmlslides Elo1127

Design ArenaMuse Wonder (max) Agents Arena Pdf Elo1205

Design ArenaMuse Wonder (max) Agents Arena Python-Pptxslides Elo1026

Design ArenaMuse Wonder (max) Agents Arena Spreadsheet Elo1248

Design ArenaMuse Wonder (max) Models Arena 3D Elo1431

Design ArenaMuse Wonder (max) Models Arena Code Categories Elo1392

Design ArenaMuse Wonder (max) Models Arena Data Visualization Elo1292

Design ArenaMuse Wonder (max) Models Arena Game Development Elo1414

Design ArenaMuse Wonder (max) Models Arena UI Component Elo1362

Design ArenaMuse Wonder (max) Models Arena Website Elo1378

Vals AIWonder Access to Justice Benchmark73.0%

Vals AIWonder BioMysteryBench67.0%

Vals AIWonder Code Migration v1.172.4%

Vals AIWonder CyberBench v1.180.4%

Vals AIWonder EMB v1.172.5%

Vals AIWonder Finance Agent v2.165.5%

Vals AIWonder Vals Finance Index61.2%

Vals AIWonder Financial Coaching Bench73.8%

Vals AIWonder HLAB-Vals-1.123.8%

Vals AIWonder Immigration69.6%

Vals AIWonder IOI66.9%

Vals AIWonder Vals Legal Index75.3%

Vals AIWonder Legal Research Bench50.5%

Vals AIWonder MysteryMechanism27.5%

Vals AIWonder ProofBench v1.184.0%

Vals AIWonder Public Benefits Bench v1.170.2%

Vals AIWonder Vals Science Index39.1%

Vals AIWonder SWE-bench Multimodal45.6%

Vals AIWonder Tax Agent Bench36.3%

Vals AIWonder Terminal-Bench 4.049.5%

Vals AIWonder Terminal-Bench-Science22.9%

Vals AIWonder Vals Index64.9%

Vals AIWonder Vibe Code Bench 1-10026.6%

Vals AIWonder Vibe Code Bench v1.183.1%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

1.

Claude Code

Claude Code is Anthropic's agentic coding tool that reads your entire codebase, plans and executes changes across files, runs tests, and iterates on failures, all from natural language prompts.

17.9Btokens

2.

Plato Computer Use Agent

new

14.7Btokens

3.

Portkey AI

Control panel for AI apps

11.9Btokens

4.

pareto-autoresearch

new

10.9Btokens

5.

pi

There are many coding agents, but this one is yours.

7.26Btokens

Rest of OpenRouter

8.63B

Top 5 Apps

601M

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions

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 a 1M-token context window.

Muse Wonder costs $4.00/M input tokens and $20.00/M output tokens, with separate rates for Cache Read at $0.20/M tokens.

Muse Wonder has a 1,048,576 token context window.

Yes. Muse Wonder accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Muse Wonder accepts text, images, video, files such as PDFs, and audio as input and returns text.

Muse Wonder is served by 2 providers on OpenRouter: Google Vertex and Meta. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.

Muse Wonder was released on October 12, 2026.

正文以来源语言显示。

参考来源

← 返回每日简报