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
- Long prompts: “Muse Ember has two price tiers, and the input tokens in your API request set the tier, cached tokens included. When a request continues a stored conversation with previous_response_id, its input includes that conversation. 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.” (documentation page, read November 10, 2026)
- What it is for: “For hard single-shot coding problems, knowledge-heavy questions, or visual coding, use Muse Spark or Muse Wonder.” (documentation page, read November 10, 2026)
- Ways to buy it: “On Model API, Muse Ember runs in Standard mode only; it has no Contributor-mode variant.” (documentation page, read November 10, 2026)
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:
- Muse Spark 1.3 1.0M tokens $1.25 in · $4.25 out
- Muse Spark 1.2 1.0M tokens $1.25 in · $4.25 out
- Muse Spark 1.1 1.0M tokens $1.25 in · $4.25 out
- Muse Wonder 1.0M tokens $4.00 in · $20.00 out
Mentioned in
One post on AI Signal cites Muse Ember. The sentence is the post's own, taken from where it links here.
-
AI Pricing This Week: Fable 5.2, Gemini 4 Carbon, Nov 9-15 · November 16, 2026
| Model | Released | Added here | Input / output per 1M tokens | |---|---|---|---| | Claude Fable 5.2 | November 9 | November 10 | $8.00 / $40.00 | | Claude Mythos 5.2 | November 9 | November 10 | $8.00 / $40.00, verification required | | Muse Ember | November 9 | November 10 | $0.10 / $0.50 up to 200K input tokens | | Gemini 4 Carbon | November 10 | November 11 | $2.00 / $10.00 through November 30, then $4.00 / $20.00 | | Gemini 4 Hydrogen | November 12 | November 13 | $1.50 / $7.50 | | GPT-6 Rosalind | no date | November 9 | $15.00 / $75.00, restricted |
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
- Muse Spark 1.3 Muse $1.25 in · $4.25 out
- Muse Spark 1.2 Muse $1.25 in · $4.25 out
- Muse Spark 1.1 Muse $1.25 in · $4.25 out
- Muse Wonder Muse $4.00 in · $20.00 out
Cheaper or equally priced alternatives
Current models with an input price at or below $0.10 per 1M tokens.
- GPT-6 Luna OpenAI $0.10 in · $0.50 out
- Claude Haiku 5.5 Anthropic $0.10 in · $0.50 out
- Gemini 2.5 Flash-Lite Google $0.10 in · $0.40 out
- Ministral 3 3B Mistral $0.10 in · $0.10 out
Compare every model in one table →
Work out what this costs at your volume →