Meta logo

Muse Ember

Meta Superintelligence Labs' smallest closed-weight Muse model, built for high-volume agent work such as sub-agent tasks, tool calls, routing and extraction.

Context
1M tokens
Max output
524K
Released
Visit Meta Compare vs other LLMs →

Hosted API price

List price via Meta · per 1M tokens

USD
Input
$0.10 /1M
Output
$0.50 /1M
Hosted by
Meta 1 provider

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

  • Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Muse Ember, cheapest input first. Set your monthly volume to see what each would bill.

Every provider serving Muse Ember, with its price per 1M input and output tokens and what the volume above would cost
Provider Input /1M Output /1M Cached input /1M Cost at 10M in + 2M out Link
Meta logo Meta Creator $0.10 $0.50 $0.004 $2.00 Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Similarly priced models

The models nearest Muse Ember by blended rate, each at its own cheapest provider.

Models priced nearest Muse Ember per 1M tokens, each at its cheapest provider
Model Blended /1M Input /1M Output /1M Context Cutoff vs Muse Ember
Mistral Ministral 3 8B Mistral $0.15 $0.15 $0.15 256K −10%
Meta Llama 3.2 11B Vision Meta $0.1535 $0.049 $0.676 128K Dec 2023 −8%
Xiaomi MiMo MiMo-V2.6-Flash Xiaomi MiMo $0.1633 $0.14 $0.28 1M −2%
Anthropic Claude Haiku 5.5 Anthropic $0.1667 $0.10 $0.50 1M Jun 2026 0%
OpenAI GPT-6 Luna OpenAI $0.1667 $0.10 $0.50 1M May 2026 0%
Meta Muse Ember This model Meta $0.1667 $0.10 $0.50 1M
MiniMax MiniMax-M3.1-Flash MiniMax $0.1688 $0.1125 $0.45 1M +1%
Google Cloud Gemma 4 31B Google Cloud $0.17 $0.13 $0.37 256K Jan 2025 +2%
Meta Llama 3.3 70B Meta $0.1792 $0.135 $0.40 128K Dec 2023 +8%
Alibaba Cloud Qwen3.5-27B Alibaba Cloud $0.1863 $0.086 $0.688 262K +12%
Tencent Hy3 Tencent $0.198 $0.132 $0.528 262K +19%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Capabilities

What Muse Ember accepts and can do, as published by Meta.

  • Text Accepts and generates natural-language text.
  • Image Accepts images as input alongside text.
  • Video Accepts video as input.
  • Audio Accepts audio as input.
  • Reasoning Thinks before it answers, always on or as a switchable mode.
  • Function calling Connect to external tools, APIs, and systems.
  • Structured output Return responses in structured formats like JSON.
  • Web search Search the web for up-to-date information.
  • File upload Process uploaded documents, spreadsheets, and other files.

Common questions

What is Muse Ember good for?

Repeated, high-volume work inside agents: sub-agent coding tasks, tool calls, routing, and extraction or classification across large batches of images, files and records. Meta suggests pairing it with Muse Spark or Muse Wonder, with the larger model planning. It sits at the low end of Meta's API price range.

When is Muse Ember not a good fit?

Self-hosting: the weights are closed, and Meta publishes no parameter count or knowledge cutoff. Meta points hard single-shot coding problems, knowledge-heavy questions and visual coding to Muse Spark or Muse Wonder, and a request over 200K input tokens is billed in full at a higher rate.

What is the cheapest way to run Muse Ember?

The cheapest hosted rate is $0.10 / $0.50 per 1M tokens via Meta.

Can I self-host Muse Ember?

No. Meta does not publish the weights; Muse Ember is available only through hosted APIs.

More from Meta

  • Llama 3.3 70B Open weights 128K context · cutoff Dec 2023
    From $0.135 / $0.40 /1M in / out at the cheapest provider
  • Llama 3.2 11B Vision Open weights 128K context · cutoff Dec 2023
    From $0.049 / $0.676 /1M in / out at the cheapest provider
  • Llama 4 Scout Open weights 10M context · cutoff Aug 2024
    From $0.16 / $0.64 /1M in / out at the cheapest provider
  • Llama 3.2 3B Open weights 128K context · cutoff Dec 2023
    From $0.051 / $0.335 /1M in / out at the cheapest provider
  • Muse Glimmer 30B Open weights 131K context · cutoff Jan 2026
    From $0.20 / $0.80 /1M in / out at the cheapest provider
  • Llama 3 8B Open weights 8K context · cutoff Mar 2023
    From $0.05 / $0.25 /1M in / out at the cheapest provider
  • Llama 4 Maverick Open weights 1M context · cutoff Aug 2024
    From $0.25 / $0.87 /1M in / out at the cheapest provider
  • Llama 3.2 1B Open weights 128K context · cutoff Dec 2023
    From $0.027 / $0.201 /1M in / out at the cheapest provider
All Meta models