Muse Ember
Last verified November 11, 2026 · Meta pricing ↗$0.100/1M input · $0.500/1M output · 1.0M context · Meta
Muse Ember costs $0.100 per 1M input tokens and $0.500 per 1M output tokens from Meta, with a 1.0M-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0003, or $3.50 per 10,000 requests. On that workload it is cheaper than 147 of the 172 other buyable models tracked here.
Count Tokens
—
Tokens
—
Input Cost
—
Output Cost
Estimate Monthly Cost
Monthly Cost Estimator
Quick:
<$0.0001/mo
Pick a preset above or enter custom usage
What Muse Ember Costs Per Request
At $0.100 per 1M input and $0.500 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0003 | $3.50 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.0011 | $11.00 |
| Coding-agent step | 30,000 / 2,000 | $0.0040 | $40.00 |
Muse Ember vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Muse Ember Meta | $0.100 | $0.500 | 1.0M | $0.0011 |
| Llama 4 Scout Meta | $0.080 | $0.300 | 1.0M | $0.0008 |
| GPT-6 Luna OpenAI | $0.100 | $0.500 | 1.1M | $0.0011 |
| Claude Haiku 5.5 Anthropic | $0.100 | $0.500 | 1.0M | $0.0011 |
Alternatives to Muse Ember
Pricing Details
MetaMeta's smallest Muse model, launched November 9, 2026, the first trained using Muse Wonder Full. Model ID muse-ember-1.0. Standard mode only (no Contributor tier). Up to 200K input tokens: $0.10 input, $0.004 cached input, $0.50 output. LONG CONTEXT: above 200,000 input tokens (cached tokens and stored previous_response_id conversation included) the WHOLE request bills $0.30 / $0.012 / $1.50. No cache-write charge listed, no batch discount. Web search $2.50 per 1,000 queries. 3,000 RPM / 4M TPM per team. Default reasoning effort max (minimal to max). Text, image, video, audio and PDF input; text output. Responses, Chat Completions and Messages endpoints; Muse Code; Meta says also Google Cloud and Oracle Cloud. Not open weights. Same short-prompt input/output as Claude Haiku 5.5 and GPT-6 Luna, but cached input is $0.004 vs their $0.01 and Haiku's long tier starts at 100K. Artificial Analysis Intelligence Index v5.0.1: max 36.0 at $0.136 per task (84.5K output tokens per task, 454 tok/s), xhigh 34.1 at $0.116; Haiku 5.5 max 36.5 at $0.411, GPT-6 Luna max 27.9 at $0.152. AA-Omniscience 21.1% accuracy, 17.4% hallucination rate, declines 64%. AutomationBench (AA) 68.1 partial credit / 37.8 strict. Estimated tokens (different tokenizer).
Input / 1M tokens
$0.1
Output / 1M tokens
$0.5
Context Window
1.0M
Max Output
524K
Price History
Launched at current price on 2026-11-09. No price changes recorded since.
Frequently Asked Questions
Common questions about Muse Ember pricing and usage
How much does Muse Ember cost?
Muse Ember costs $0.1 per 1 million input tokens and $0.5 per 1 million output tokens. This pricing is set by Meta.
What tokenizer does Muse Ember use?
Muse Ember uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.
What is Muse Ember's context window?
Muse Ember supports a context window of 1.0M tokens (1,048,576 tokens). The maximum output length is 524K tokens.
How does Muse Ember compare to other models?
On an 8,000-token-in, 600-token-out RAG answer, Muse Ember costs $0.0011 per request. The nearest-priced alternatives cost: Llama 4 Scout (Meta) $0.0008, GPT-6 Luna (OpenAI) $0.0011, Claude Haiku 5.5 (Anthropic) $0.0011. The table above lists their full rates and context windows.
How do I count tokens for Muse Ember?
Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Muse Ember using the cl100k_base tokenizer.