UncoverAI
AI Models

LLM · Meta

Muse Embermuse-ember-1.0

Maker's stated useEfficient execution model for high-volume, repeated workChecked 13 Nov 2026 Source

Meta's model page lists muse-ember-1.0 with a context window of 1,048,576 tokens and a max output of 524,288 tokens. Input is text, image, video, audio, and PDF, and output is text. The pricing page lists Standard mode rates for requests of up to 200K input tokens at $0.10 input, $0.004 cached input, and $0.50 output per 1M tokens. A request with more than 200K input tokens is billed entirely at $0.30 input, $0.012 cached input, and $1.50 output. The stored figures are the up-to-200K rates. Contributor mode is not available for Muse Ember on Model API. Standard mode says content is not used to train Meta models. The launch post dated November 9, 2026 says Muse Ember is available on Google Cloud and Oracle Cloud.

Caching and batch

  • Live API Not stated by vendor
  • Cache read $0.004
  • Cache write is Not stated by vendor
  • Cache TTL is Not stated by vendor
  • Minimum cacheable tokens are Not stated by vendor
  • Batch discount is Not stated by vendor
  • Batch input / output are Not stated by vendor

Standard mode. A request with more than 200K input tokens is billed in full at $0.30 input, $0.012 cached input, and $1.50 output per 1M tokens.

Checked 10 Nov 2026 Source

Checked 10 Nov 2026https://dev.meta.ai/docs/muse-ember