# Muse Wonder

Muse Wonder is Meta's reasoning model for complex software engineering and long-running personal and professional agents. It is built to track context across many steps, make and verify changes across a codebase, call tools in parallel, and recover from errors while following detailed instructions. Its published context window is 1,048,576 tokens. The advertised input rate is $4.00 per million input tokens. The advertised output rate is $20.00 per million output tokens.

- Model identifier: ` meta/muse-wonder `
- Creator: Meta
- Providers: Meta
- Model type: Text generation
- Canonical model page: [Muse Wonder](<https://impossibl.com/meta/muse-wonder>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-10-12

## Providers

Meta hosts Muse Wonder. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

| Provider | Endpoint location | Routes | Verified context window | Tool calling |
| --- | --- | --- | --- | --- |
| Meta | Not specified | 1 | Not verified | Not verified |

The model price applies whichever provider serves the request. Endpoint locations do not guarantee inference residency.

## Specs and Capabilities

- Context window: 1,048,576 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text, image
- Outputs: text
- Tool calling: Not published

## API access

Use ` meta/muse-wonder ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $4.00 | per million input tokens |
| Output | $20.00 | per million output tokens |
| Cache read | $0.20 | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Benchmarks

Last checked: 2026-10-14T16:55:49.515Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### Muse Wonder (Max)

Source: [Evaluation source](<https://artificialanalysis.ai/models/muse-wonder>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 52.39 |
| Omniscience Index | 25.48 |
| Humanity’s Last Exam | 50.09% |
| SciCode | 60.30% |
| CritPt | 28.29% |
| AA-LCR | 80.67% |
| Harvey LAB | 10.00% |
| GDPval Elo | 1770.34 |
| GDP.pdf All-pass | 30.60% |
| AutomationBench Partial | 68.09% |
| legal index (API) | 52 |
| economics index (API) | 57.7 |
| engineering index (API) | 53.8 |
| intelligence index (API) | 52.4 |
| strategy and ops index (API) | 54.8 |
| finance and accounting index (API) | 51.3 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/meta/muse-wonder/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Muse Wonder?

Muse Wonder is Meta's reasoning model for complex software engineering and long-running personal and professional agents. It is built to track context across many steps, make and verify changes across a codebase, call tools in parallel, and recover from errors while following detailed instructions.

Sources: [Meta Model API: Muse Wonder](<https://dev.meta.ai/docs/models#muse-wonder>); [Meta research announcement: Muse Wonder](<https://research.meta.ai/blog/introducing-muse-wonder/>)

### How much does Muse Wonder cost?

Muse Wonder costs $4.00 per million input tokens and $20.00 per million output tokens through the Impossibl API. Cache reads cost $0.20 per million tokens. All rates are in USD.

### What is the context length of Muse Wonder?

Muse Wonder has a 1,048,576-token context window through the Impossibl API.

### What inputs and outputs does Muse Wonder support?

Muse Wonder accepts text and image as input. Muse Wonder returns text.

### How do I use Muse Wonder through an API?

Muse Wonder is available through the Impossibl API. Use meta/muse-wonder as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was Muse Wonder released?

Meta released Muse Wonder on October 12, 2026.

Sources: [Creator release announcement](<https://about.fb.com/news/2026/10/introducing-muse-wonder-models/>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Muse Wonder: model details and pricing](<https://impossibl.com/meta/muse-wonder>)
- [Model directory](<https://impossibl.com/models>)
- [Meta Model API: Muse Wonder](<https://dev.meta.ai/docs/models#muse-wonder>)
- [Meta research announcement: Muse Wonder](<https://research.meta.ai/blog/introducing-muse-wonder/>)