Muse Ember

Muse Ember from Meta is an efficient reasoning model built for high-volume agent tasks, including tool calls, coding subtasks, routing, extraction, and long-document processing. It accepts text and image inputs with a 1M-token context window and up to 524,288 output tokens. Pair it with Muse Wonder or Muse Spark 1.3 for multi-step planning and reasoning.

Requests on the global /locations/global/publishers/meta/v1/responses endpoint pass the bare model ID muse-ember-1.0 in the model field. For an example request, see Use Meta models.

View model card in Model Garden

Model ID meta/muse-ember-1.0
Launch stage Preview
Supported inputs & outputs
  • Inputs:
    Text, Image
  • Outputs:
    Text
Token limits
  • Maximum input tokens: 1,048,576
  • Maximum output tokens: 524,288
Capabilities
Usage types
Versions
  • meta/muse-ember-1.0
    • Launch stage: Preview
    • Release date: November 9, 2026
Supported regions

Model availability

  • Global
    • global endpoint
Quota limits

global endpoint:

  • Context length: 1,048,576

Pricing See Pricing.

Inference parameters and limitations

Keep the following inference parameters and limitations in mind when sending requests:

  • Reasoning effort: Set reasoning.effort to minimal, low, medium, high, xhigh, or max (use xhigh or max for agentic and coding work). none isn't supported. Pricing is the same at every effort level.
  • Reasoning output: Reasoning content is returned in encrypted form for multi-turn replay. Reasoning summaries are returned at higher effort levels and might be absent at lower ones.
  • Tool calling: Supports built-in tool calling with Model Context Protocol (MCP) support. tool_choice supports auto only (none, required, and named-function choices aren't supported).
  • Recommended sampling: temperature 1.0, top_p 1.0 (top_k disabled).
  • Recommended pairing: Pair Muse Ember with Muse Wonder for complex open-ended coding, or use retrieval for knowledge-heavy recall.
  • Known limitations: Audio, video, and PDF inputs, chat completions, and stateful response storage (store: true) aren't supported. For the full capability list, see the table earlier on this page.

What's next