As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/muse-ember-1-0/

# Muse Ember 1.0

Meta, Muse family. Status: current. Type: reasoning model. Released: 2026-11-09. Training cutoff: not published.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| Meta Model API | `muse-ember-1.0` | https://api.meta.ai/v1/chat/completions | https://dev.meta.ai/docs/ |

## Pricing

- Input: $0.10 per 1M tokens
- Cached input: $0.004 per 1M tokens
- Output: $0.50 per 1M tokens
- Unit as published: per 1M tokens (USD) for prompts up to 200K tokens; $0.30 / $0.012 cached / $1.50 above 200K
- Source: https://simonwillison.net/2026/Nov/10/muse-ember/
- Last checked: 2026-11-10

## Specs

- Input: text, image, audio
- Output: text
- Context window: 1,000,000 tokens
- Max output: not published
- Open weights: no
- Licence: proprietary

## What it has not seen

- No published training cutoff. Counted from its release (2026-11-09): at least 65 AI events since (16 major, 1 historic), as of 2026-11-13.
- Everything since October 2026: https://postcutoff.com/since/2026-10/

## What stands out

- Cheap agent workhorse: Meta's smallest Muse model for tool calls, routing, extraction and long-document parsing; six reasoning levels; AA Intelligence Index about 34-36 at roughly $0.12-0.14 per index task. Source: https://research.meta.ai/blog/muse-ember

## Notes

Pairs with Muse Wonder ('Muse Wonder plans, Muse Ember handles the volume'). Endpoint assumed same as other Muse API models; check docs.


Model page: https://postcutoff.com/m/muse-ember-1-0/