Muse Ember pricing and specs

Muse Ember is Meta's smallest and most efficient reasoning model, built for the work agents repeat all day: tool calls, coding subtasks, routing, extraction, and long-document parsing. It pairs with Muse Wonder or Muse Spark, which plan while Muse Ember handles the volume.

8,28 ₽input / 1M$0.1
41,38 ₽output / 1M$0.5
1.0Mcontexttokens
524Kmax outputtokens

Muse Ember price per 1M tokens

Type₽ / 1M$ / 1M
Input tokens8,28 ₽$0.1
Output tokens41,38 ₽$0.5
Cache read0,33 ₽$0.004

Prices in rubles as of 10.11.2026 at the CBR rate: 1 $ = 82.75 ₽.

Muse Ember specs and limits

Context window
1.0M
Max output
524K
Input
text, image, video, pdf, audio
Output
text
Family
muse
Released
2026-11-09
Updated
2026-11-09
Also known as
meta ember, meta ai ember, meta platforms ember, muse spark ember, llama ember

What Muse Ember can do

  • ✓Reasoning
  • ✓Tool calling
  • ✓Structured output
  • ✓Attachments / files
  • ✓Vision (images)
  • ✓Temperature control
  • —Open weights

Muse Ember benchmarks

BenchmarkScoreMetric
AutomationBench37.8strict pass@1
Agents' Last Exam61.6score
Terminal-Bench40.9accuracy
FrontierCode27.2score
GDP.pdf22.8score
OSWorld69.5mean partial score
OSWorld33.8binary completion rate
PerceptionBench80.6score
Artificial Analysis Intelligence Index36index score

Frequently asked questions

How much does the Muse Ember API cost?

Input costs $0.1 per 1M tokens (8.28 ₽) and output costs $0.5 per 1M (41.38 ₽). Meta bills the prompt and the completion separately, so the price of a call depends on how long both are. Ruble figures use the Bank of Russia rate of 82.75 ₽ per dollar for November 2026.

How much do 1,000 Muse Ember tokens cost?

List prices are quoted per 1M tokens, so 1,000 tokens cost a thousandth of that: divide $0.1 for input and $0.5 for output by 1,000. The same rates in rubles are 8.28 ₽ and 41.38 ₽ per 1M tokens. Both prompt tokens and completion tokens are billed.

How many tokens does Muse Ember hold?

The Muse Ember context window is 1.0M tokens (1,048,576). Everything shares that budget: the system prompt, the dialogue history, attached files and the answer the model writes. The figure comes from the Meta model card as of November 2026.

What are the Muse Ember limits?

The context window is 1.0M tokens (1,048,576) and a single response is capped at 524K tokens, so longer output has to be generated in parts. Rate limits are set by Meta per account and depend on your plan rather than on the model, so they are not listed here.

How is the Muse Ember price in rubles calculated?

Providers quote their tariffs in US dollars, so the ruble amounts here are a conversion at the official Bank of Russia rate of 82.75 ₽ per dollar. For Muse Ember that gives 8.28 ₽ per 1M input tokens and 41.38 ₽ per 1M output tokens. When the rate moves, the ruble price moves with it.

How is Muse Ember different from other Meta AI models?

Muse Ember belongs to the Muse family at Meta. Models in the Meta AI line differ in context size, price per 1M tokens and supported capabilities, so compare them by the numbers on their cards rather than by the name. Every Meta AI model is listed on the provider page.

Can Muse Ember reason?

Yes, Muse Ember declares a reasoning mode: it works through intermediate steps before it answers. Those steps add output tokens, so a call with a long reasoning chain costs more and takes longer than a plain completion. Capabilities declared for the model: reasoning, tool calling, image input, structured output.

What capabilities does Muse Ember support?

The declared capabilities of Muse Ember are: reasoning, tool calling, image input, structured output. It accepts text, images, video, PDF, audio as input, and every attachment consumes tokens from the shared context window of 1.0M tokens. The list comes from the Meta model card and is refreshed with the catalog as of November 2026.

Other Meta models