meta/muse-ember

Model release OpenRouter 模型 Source language: Chinese

OpenRouter 于 2026-11-10 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:$0.1000/百万 tokens;输出价:$0.5000/百万 tokens;定位(来源描述):Muse Ember is the smallest and most efficient model from Meta that’s designed for complex…

Full text

Meta: Muse Ember

meta/muse-ember

Compare

Muse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing, extraction, and long document parsing.

Muse Ember accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.

Modalities

In / out price

$0.10 / $0.50per 1M

Context

1.0M

Released

Nov 9, 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

$0.10$0.50$0.0041.67s219 tok/s

100.00%

$0.10$0.50$0.0041.87s246 tok/s

100.00%

ProviderInput / Output /M

Input $0.10 / Output $0.50

219 tok/s100.00% uptime

Input $0.10 / Output $0.50

246 tok/s100.00% 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

$0.02687/M tokens

Output

$0.4998/M tokens

Muse Ember — Price history

Price history

No effective price data for this selection

$0.0211$0.50082.1%40.8%

$0.0308$0.50072.1%59.2%

ProviderInput / Output /M

Token share

Effective in $0.0211 / Effective out $0.500

Token share

40.8%

Effective in $0.0308 / Effective out $0.500

Token share

59.2%

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

246tok/s

P50, best across providers

Latency

1.67s

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.

99.01%

Availability over the last 3 days

Last 72 hours

Availability 99.01%

3 Days Ago2 Days AgoYesterdayNow

Availability over the last 24 hours

OpenRouter Availability

99.31%

Without Routing

85.77%

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 Ember (Vals AI)

SourceBenchmarkScore

Vals AIMuse Ember EMB v1.172.2%

Vals AIMuse Ember Finance Agent v2.163.8%

Vals AIMuse Ember Vals Finance Index60.9%

Vals AIMuse Ember HLAB-Vals-1.125.0%

Vals AIMuse Ember Vals Legal Index75.7%

Vals AIMuse Ember Legal Research Bench49.0%

Vals AIMuse Ember Tax Agent Bench38.2%

Vals AIMuse Ember Terminal-Bench 4.039.4%

Vals AIMuse Ember Vals Index60.5%

Vals AIMuse Ember Vibe Code Bench v1.183.7%

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.

DeepSeek Harness

new

65.9Btokens

2.

Freebuff

Powerful coding models, funded by ads

32.4Btokens

3.

Hermes Agent

Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.

20.3Btokens

4.

pi

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

19.6Btokens

5.

Bitbison triage

new

15.8Btokens

Rest of OpenRouter

43.2B

Top 5 Apps

20.8B

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 Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing, extraction, and long document parsing. Muse Ember accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.

Muse Ember costs $0.10/M input tokens and $0.50/M output tokens, with separate rates for Cache Read at $0.004/M tokens.

Muse Ember has a 1,048,576 token context window. It supports up to 524,288 completion tokens.

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

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

Muse Ember 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 Ember was released on November 9, 2026.

Sources

← Back to the daily brief