Meta · Model
Muse Ember API pricing, cost and context window
Muse Ember costs $0.10 per million input tokens and $0.50 per million output tokens. Cached input costs $0.004. It reads up to 1,048,576 tokens. Prices checked 2026-11-22. By blended price it is number 2 of Meta’s 7 current models here, counting from the cheapest.
- Input / 1M
- $0.10
- Output / 1M
- $0.50
- Cached / 1M
- $0.004
- Context
- 1,048,576
- Max output
- Not published
- Released
- 2026-11-09
Estimate your cost with Muse EmberCompare all Meta modelsCount tokens for Muse Ember
Pricing
How much does Muse Ember cost per million tokens?
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $0.10 | $0.50 |
| Cached input (read) | $0.004 | – |
| Cache write | $0.125 | – |
Output costs 5.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 4% of the normal input price.
Work out your monthly Muse Ember bill in the cost calculatorSee what prompt caching saves
Examples
How much does a typical Muse Ember request cost?
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.000278 | $8.46 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.000735 | $11.18 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.00193 | $11.73 |
| Document summariser | 8,000 / 600 | 300 | $0.0011 | $10.04 |
Change any number in the cost calculator.
Context
What is Muse Ember’s context window and max output?
Muse Ember accepts up to 1,048,576 tokens per request, roughly 786,432 English words or 1,573 pages. That budget is shared between your prompt and the reply, and no separate cap on the reply is published.
Filling the whole window with one prompt costs about $0.10 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
What can Muse Ember do?
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- No
- Accepts
- text, image, video, file, audio
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
What is the Muse Ember API model ID?
- OpenRouter
meta/muse-ember
Use the OpenRouter ID when calling it through OpenRouter; Meta’s own API may name it differently. See the model ID reference for the providers we document.
Meta
Where does Muse Ember sit in Meta’s line-up?
Ranked by blended price (three parts input to one part output, $0.20 per 1M for Muse Ember), it is number 2 of Meta’s 7 current models here, counting from the cheapest. One step down, Llama 4 Scout costs $0.15 blended (25% less). Unlike Muse Ember, it doesn’t accept files, audio or video, reads up to 327,680 tokens (1,048,576 here) and has no reasoning mode. One step up, Llama 4 Maverick costs $0.5125 (2.6× as much). Unlike Muse Ember, it doesn’t accept files, audio or video, reads up to 524,288 tokens (1,048,576 here) and has no reasoning mode. See every Meta model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Llama 4 Scout | $0.10 | $0.30 | 327,680 | 2025-04-05 |
| Muse Ember (this page) | $0.10 | $0.50 | 1,048,576 | 2026-11-09 |
| Llama 4 Maverick | $0.35 | $1 | 524,288 | 2025-04-05 |
| Muse Glimmer 30B | $0.35 | $1.50 | 131,072 | 2026-08-09 |
| Muse Spark 1.3 | $1.25 | $4.25 | 1,048,576 | 2026-09-02 |
| Muse Spark Open | $1.25 | $4.25 | 1,048,576 | 2026-10-15 |
| Muse Wonder | $4 | $20 | 1,048,576 | 2026-10-12 |
Meta’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
Save
What are cheaper alternatives to Muse Ember?
- Gemma 4 26B A4BGoogle47% cheaper
- Seed-2.0-MiniByteDance Seed13% cheaper
- Qwen3.5-9BQwen5% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Which models cost about the same?
- GPT-6 LunaOpenAI$0.10 / $0.50
- Claude Haiku 5.5Anthropic$0.10 / $0.50
- Ministral 3 14B 2512Mistral$0.20 / $0.20
- Qwen3.5-9BQwen$0.17 / $0.25
- Seed-2.0-MiniByteDance Seed$0.10 / $0.40
Current models from other major providers, closest blended price.
FAQ
Muse Ember questions
How much does Muse Ember cost?
Muse Ember costs $0.10 per million input tokens and $0.50 per million output tokens, with cached input at $0.004. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00035. Use the LLM cost calculator for your own workload.
What is Muse Ember’s context window?
1,048,576 tokens, about 786,432 English words or 1,573 printed pages, shared between your prompt and the reply. No separate limit on the reply is published, so the window is the limit.
Does Muse Ember support prompt caching and batch requests?
Yes, cached input is billed at $0.004 per million tokens (4% of the normal input price), and writing a prompt to the cache costs $0.125 per million tokens. No batch price is published for it.
What are cheaper alternatives to Muse Ember?
With the same essentials (image input and tool calling), the cheapest options are Gemma 4 26B A4B (47% cheaper), Seed-2.0-Mini (13% cheaper), Qwen3.5-9B (5% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Muse Ember?
On OpenRouter it is meta/muse-ember. Meta’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
When was Muse Ember released?
Muse Ember was first listed on 2026-11-09. It is the first model in its line in our data. Release dates here are when our price source first listed each model.
Is Muse Ember open source?
No, Muse Ember is only available through Meta’s API and partners; its weights aren’t published.
Keep exploring