Muse Ember
- Family
- Muse
- Released
- 2026-11-09
- Context
- 1M
- Max output
- 512K
- Specialization
- general
- Openness
- Proprietary
- License
- ProprietaryRestricted
- Weights
- Not released
- Code
- Unknown
- Training
- Pretrained
Large-scale open-source AI for social technologies.
Cheapest of 3 routes · Meta Model API · cache read $0.004
Large-scale open-source AI for social technologies.
Cheapest of 3 routes · Meta Model API · cache read $0.004
About
Muse Ember is Meta Superintelligence Labs' smallest and most efficient Muse model, introduced November 9, 2026, for the work agents repeat all day: tool calls, coding subtasks, routing, extraction and long-document parsing. Meta says it is the first model trained using Muse Wonder Full. It takes text, image, audio and video input and returns text, with a 1M-token context window and up to 512K output tokens, and supports the Responses API.
Providers(3)
Compare all 3Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Cache | Route |
|---|---|---|---|---|
| Meta Model API | $0.100 | $0.500 | read $0.004 | Serverless |
| OpenRouter | $0.100 | $0.500 | read $0.004 | Serverless |
| Vercel AI Gateway | $0.100 | $0.500 | read $0.004 | Serverless |
Capabilities
Benchmark peer barsfor RAG
No task-mapped benchmark peers are available for this model yet.
Migration checks
No linked migration route is available for this model yet.
API versions
muse-ember-1.0