DevTk.AI

Muse Ember 1.0

Meta

Muse Ember 1.0 by Meta: $0.1/M cache-miss input, $0.5/M output tokens. Cached input: $0.004/M. Long-context pricing at or above 200K input tokens: $0.3/M input, $1.50/M output. 1.0M context, 524K max output. Vision & Video. Price verified 2026-11-18.

Input Price

$0.1

cache miss / 1M tokens

Cached Input

$0.004

per 1M tokens

Output Price

$0.5

per 1M tokens

Context Window

1.0M

tokens

Muse Ember 1.0 price history

Per 1M cache-miss input / output tokens. See all AI API price changes

  • 2026-11-09Launch price$0.1 / $0.5

    Smallest Muse model on the Meta Model API. Cache hits $0.004/M. Requests above 200K input tokens bill entirely at $0.30/$1.50. Meta Model API pricing

Specifications

ProviderMeta
Model IDmuse-ember-1.0
Input Price$0.1 / 1M cache-miss tokens
Cached Input Price$0.004 / 1M tokens
Output Price$0.5 / 1M tokens
Long Context Threshold200K input tokens
Long Context Pricing$0.3 / 1M cache-miss input, $0.012 / 1M cached input, $1.50 / 1M output
Context Window1.0M tokens
Max Output524K tokens
Capabilities
textvisionvideoaudiofunction_callingstructured_output
Release Date2026-11-09
Pricing SourceOfficial Meta pricing
Price Verified2026-11-18
NotesSmallest and most efficient Muse model, for high-volume sub-agents, tool calls, routing and extraction. Requests above 200K input tokens bill entirely at the higher rates. Standard mode only.

Monthly Cost Estimates

Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.

Daily TokensMonthly CostAnnual Cost
10K $0.09 $1.08
50K $0.45 $5.40
100K $0.9 $10.80
500K $4.50 $54.00
1.0M $9.00 $108.00

How Muse Ember 1.0 Pricing Compares

Standard cache-miss input / output prices per 1M tokens, compared with active, price-verified models priced in USD. Cached, batch and long-context rates are not included.

  • Within Meta: none of the 2 other active Meta models has a lower input price, and none has a lower output price.
  • Similar context window: among the 64 active models with a 524K–2.1M token context window, Muse Ember 1.0 ranks #6 from cheapest at a 50/50 input/output mix. Cheapest: Qwen3.7 Flash ($0.03/$0.13). Most expensive: GPT-5.5 Pro ($30.00/$180.00).

Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.

Muse Ember 1.0 Key Details

  • Pricing: $0.1/M cache-miss input tokens, $0.004/M cached input tokens, $0.5/M output tokens
  • Context window: 1.0M tokens — 14 of 90 active models we track have a larger window
  • Max output: 524K tokens per response
  • Capabilities: text, vision, video, audio, function_calling, structured_output
  • Highlights: Smallest and most efficient Muse model, for high-volume sub-agents, tool calls, routing and extraction. Requests above 200K input tokens bill entirely at the higher rates. Standard mode only.
  • Released: 2026-11-09

Other Meta Models

Similar Price Range

Related Tools

FAQ

How much does Muse Ember 1.0 cost?

Muse Ember 1.0 costs $0.1 per million cache-miss input tokens and $0.5 per million output tokens. Cached input costs $0.004 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $1.05/month before cache-hit savings.

What is Muse Ember 1.0's context window?

Muse Ember 1.0 supports a context window of 1.0M tokens. This means your combined input prompt and output response can be up to 1.0M tokens. The maximum output per response is 524K tokens.

Is Muse Ember 1.0 good for my use case?

Muse Ember 1.0 supports text, vision, video, audio, function_calling, structured_output. We track pricing and limits, not output quality, so test it on your own prompts before committing. The price comparison above lists cheaper and pricier models with a similar context window, and the Pricing Calculator estimates your monthly cost across all of them.