Muse Ember
by NanoGPT · family muse · listed Nov 2026RTV
Meta's Muse Ember is the smallest and most efficient Muse model, built for the work agents repeat all day: tool calls, coding-agent subtasks, routing, and extraction. It accepts text, images, audio, video, and PDF documents across a one-million-token context window, supports tool calling and structured output, and always reasons before answering.
Current rates USD per 1M tokens
Input$0.10
Output$0.50
Cache read$0.004
Cache write—
Against the market
On the record
- Model id
meta/muse-ember- Context window
- 1.0M tokens
- Max output
- 1.0M tokens
- Input modalities
- text, image, video, audio, pdf
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-11-11
- Last updated
- 2026-11-11
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Vercel AI Gateway$0.10 in · $0.50 out
- Kilo Gateway$0.10 in · $0.50 out
- OpenRouter$0.10 in · $0.50 out