Meta: Muse Ember
meta/muse-emberMuse Ember is the smallest and most efficient model from Meta that’s designed for complex reasoning execution and the work agents repeat all day: tool calls, coding agent subtasks, routing,...
- Context window
- 1,048,576 tokens
- Input
- text · image · video · file · audio
- Output
- text
- Relay support
- Text & vision
Reference prices & points
CNY 1 = 1,000 points. The table shows site reference rates; charges use actual usage. · Price version 2
| Billing unit | Our price / CNY | Points |
|---|---|---|
| Input / 1M tokens | ¥0.86 | 860 |
| Output / 1M tokens | ¥4.3 | 4,300 |
| Per search | ¥0.0215 | 21.5 |
| Cache read / 1M tokens | ¥0.0344 | 34.4 |
| Cache write / 1M tokens | ¥1.075 | 1,075 |
Catalogue rates are for reference. The settled charge uses actual usage for that request, at the price version locked when it was reserved. Caching, long context, images and audio are charged when used. Listed prices do not mean every capability is available through this relay.
Catalogue time: 2026-11-13T17:10:12.909Z · Live catalogue
Integration & availability
Use /v1/chat/completions for non-streaming, multi-turn conversations. Models marked for vision accept images; documents can be extracted to text in the workspace. Create a site API key and ensure you have enough points and the service is enabled. Provider availability, context and budget limits apply.