Pricing · Meta

Muse Ember

Meta's muse-ember-1.0, 1.0M tokens of context. Every number on this page was read off Meta's own pricing page — never estimated, never recalled from memory.

How Meta describes it

“Muse Ember is our smallest multimodal model built for high-volume agentic workflow execution, from coding subtasks and tool calls to document summarization and extraction.”

From Meta's documentation

Pricing

Prices in US dollars per 1M tokens, as Meta's model page printed them when they were last verified, on November 10, 2026.

Input $0.10 per 1M tokens
Output $0.50 per 1M tokens
Cached input $0.004 per 1M tokens · 0.04× the input price

Long-prompt tiers

Pricing changes above a prompt-size threshold. If your average request is near the boundary, the effective rate is not the headline rate.

Condition Input Output Cached input
prompt > 200000 tokens $0.30 $1.50 $0.012

At the calculator's starting volume, 1M input tokens and 200K output tokens with no cache hits, Muse Ember costs $0.20: $0.10 for input and $0.10 for output, at the prices above. Same formula as the calculator; change the volume there.

Where this price sits

$0.10 per 1M input tokens (for prompts up to 200K tokens) is the 3rd cheapest input price of the 82 current models with a verified price on AI Signal, and the 1st of Meta's 5. Output costs 5.0× the input price.

Other current models in the Muse family:

Mentioned in

One post on AI Signal cites Muse Ember. The sentence is the post's own, taken from where it links here.

Specifications

Muse Ember's API identifier, provider and limits, from the same row of the dataset as the prices above.

API model id muse-ember-1.0
Provider Meta
Family Muse
Context window 1.0M tokens
Max output 524K tokens
Released November 9, 2026
Status Current

Muse Ember was released on November 9, 2026. It returns up to 524K tokens per response, against a context window of 1.0M tokens.

Questions about Muse Ember pricing

How much does Muse Ember cost per million tokens?
$0.10 per 1M input tokens and $0.50 per 1M output tokens for prompts up to 200,000 tokens, read on Meta's model page on November 10, 2026.
What does a cached input token cost on Muse Ember?
$0.004 per 1M cached input tokens, 4% of the $0.10 input price.
Does Muse Ember cost more for long prompts?
Yes. For prompts over 200,000 tokens it costs $0.30 per 1M input tokens and $1.50 per 1M output tokens, $0.012 for cached input, against $0.10 and $0.50 below that.

Added 2026-11-10 after the new-models scan saw meta/muse-ember in OpenRouter's catalog (a signal only; OpenRouter's price is not used). Read on 2026-11-10 from the 'Models and pricing' table of Meta's model page, which prints each cell on its own line: 'muse-ember-1.0 <200k context 1M $0.004 $0.10 $0.50' and 'muse-ember-1.0 >200k context 1M $0.012 $0.30 $1.50' (context, cached input, input, output per Mtok). Meta's 'Pricing and rate limits' page (dev.meta.ai/docs/pricing-rate-limits), same day: 'Model: muse-ember-1.0 , in Standard mode only.', 'Usage | Up to 200K input tokens (per 1M tokens) | Over 200K input tokens (per 1M tokens) |', 'Cached input | $0.004 | $0.012 |', 'Input | $0.10 | $0.30 |', 'Output | $0.50 | $1.50 |', and 'A request with up to 200K input tokens is billed at the rates in the first column. A request with more is billed at the long-context rates in full, not only for the tokens past 200K.' The same page says 'Contributor mode isn't available for Muse Wonder or Muse Ember on Model API.' Context window and max output from Meta's Muse Ember documentation (dev.meta.ai/docs/muse-ember), same day: 'Context window | 1,048,576 tokens |' and 'Max output | 524,288 tokens |'. Release: Meta's announcement (research.meta.ai/blog/muse-ember), dated 'November 9, 2026': 'Muse Ember is available today on the Meta Model API, at $0.10 per million input tokens and $0.50 per million output tokens.'

Verified November 10, 2026 against Meta's model page. Confidence: confirmed. No price change recorded for this model. How the data is checked.

Other Meta models with a verified price

Cheaper or equally priced alternatives

Current models with an input price at or below $0.10 per 1M tokens.