Muse Ember 1.0
Meta's efficient execution model for high-volume agent work: sub-agent tasks, tool calls, routing, and processing large collections of images, files, and records. Accepts text, images, video, audio, and PDF within a 1,048,576-token context, with higher rates above 200K input tokens.
Source: Muse Ember specification, Model identity and capabilities, Meta API pricing, Automatic prefix caching
- Text
- Image
- Video
- Audio
- Document
- Text
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Standard | Long context |
|---|---|---|
| Input | $0.1 / M | $0.3 / M |
| Output | $0.5 / M | $1.5 / M |
| Cache read | $0.004 / M | $0.012 / M |
Long-context rates apply above 200,000 input tokens.
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.
Provider
Where this model runs, and what it charges.
| Platform | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|
Meta | $0.1 | $0.5 | $0.004 | - | First-party API |
Price history
Has this model gotten cheaper or more expensive?
More from Meta
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every Muse Ember 1.0 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.