Muse Ember

Muse Ember is the efficient execution model in the Muse family, built for high-volume, repeated work. It runs the sub-agent tasks, tool calls, and routing inside larger agent workflows, and processes large collections of images, files, and records. Pair it with Muse Spark or Muse Wonder: the larger model plans, and Muse Ember handles the volume.

At a glance

Build with Muse Ember

Use Muse Ember for bounded work that repeats many times:

• Sub-agent tasks: run the focused coding tasks, terminal commands, and lookups that a main agent hands out.
• Tool calls: drive tool calls inside a larger workflow, where cost and latency per call add up.
• Routing: classify requests and send each one to the right handler or model.
• Work across large collections: run the same task over thousands of images, files, or records, such as captioning and sorting photos, extracting fields, or classifying tickets, with many Muse Ember requests running in parallel.

Muse Ember accepts the same request body as Muse Spark, so switching most examples is a model ID change. Switch between models lists what differs. It works with computer use, image understanding, tool calling, structured output, and search grounding.

For hard single-shot coding problems, knowledge-heavy questions, or visual coding, use Muse Spark or Muse Wonder. See Choose a model.

Pair Muse Ember with a larger model

In an agent, run Muse Wonder or Muse Spark on the main loop to plan and reason, and hand repeated subtasks to Muse Ember. The reasoning models accept the same request body, so each request picks its model with the model field. Combine models in one agent shows how to set this up in the harnesses you already use.

Make your first call

Send a request to the Responses API with your MODEL_API_KEY:

shell
curl -X POST "https://api.meta.ai/v1/responses" \
  -H "Authorization: Bearer $MODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "muse-ember-1.0",
  "input": "Classify this support ticket as billing, bug, or feature request, and give a one-sentence reason: \"I was charged twice for my October invoice.\""
}'

For the same call in Python or TypeScript, follow the quickstart and set the model to muse-ember-1.0.

Availability

Muse Ember is on Model API and in Muse Code, on pay-as-you-go and with any subscription.

On Model API, Muse Ember runs in Standard mode only; it has no Contributor-mode variant. A request with more than 200K input tokens, such as one with a long conversation history, is billed at higher long-context rates. See Muse Ember pricing for both tiers. On a Muse Code subscription, a request with more than 200K input tokens uses your plan's usage faster.

Next steps

• Weighing Muse Ember against Muse Spark and Muse Wonder? Choose a model compares them workload by workload.
• Get schema-guaranteed JSON from routing and extraction steps with structured output.