Home › Guides › Muse Ember pricing
Meta Muse Ember API pricing
Quick verdict
muse-ember-1.0 is Meta’s low-cost model: US$0.10 per 1M input tokens and $0.50 per 1M output for prompts up to 200K tokens, with cached input at $0.004. It has a 1M-token context window and takes text, image, audio and video. Muse Spark 1.3 is $1.25 / $4.25.
From Meta’s Muse Ember announcement, checked .
API prices (per 1M tokens)
| Price | Prompts ≤200K | Prompts >200K |
|---|---|---|
| Input | $0.10 | $0.30 |
| Cached input | $0.004 | $0.012 |
| Output | $0.50 | $1.50 |
Source: research.meta.ai.
Model facts
- Model ID:
muse-ember-1.0on the Meta Model API and in Muse Code; also on Google Cloud and Oracle Cloud. - Context window 1M tokens; up to 512K output tokens; supports the Responses API.
- Input: text, image, audio and video.
- Meta cites about $0.14 per task on the Artificial Analysis benchmark suite (Intelligence Index 36).
How to try it
Get a key and make a first call with our Meta Model API for beginners lesson, then swap the model name for muse-ember-1.0.
FAQ
How much does Muse Ember cost?
Meta lists muse-ember-1.0 at US$0.10 per 1M input tokens, $0.004 per 1M cached input and $0.50 per 1M output for prompts up to 200K tokens; longer prompts are $0.30 / $0.012 / $1.50. Checked Nov 9, 2026.
Is Muse Ember cheaper than Muse Spark?
Yes. Meta lists Muse Spark 1.3 at $1.25 per 1M input and $4.25 per 1M output, against $0.10 / $0.50 for Muse Ember.
Where can I use Muse Ember?
On the Meta Model API and in Muse Code, and through Google Cloud and Oracle Cloud, per Meta.
Related: Meta Model API for beginners · Meta Model API course · Meta AI · Claude Fable 5.2 pricing · Cost calculator.
Compare: Qwen4-Max pricing ($1.50 / $4.50 per 1M) and Gemini 4 Hydrogen ($1.50 / $7.50).