Muse Ember is Meta's smallest and most efficient Muse model, built for high-volume agentic execution: sub-agent tasks, tool calls, routing, extraction, coding subtasks and long-document parsing. It accepts text, images, video, audio and PDF documents and returns text, with a 1,048,576-token context window and up to 524,288 output tokens. Reasoning effort is configurable from minimal to max (default max), with automatic prompt caching and built-in web search grounding.
meta/muse-ember-1.0Nov 9, 2026+1