Meta's smallest and most efficient model, built for the work agents repeat all day: tool calls, coding subtasks, routing, extraction and long document parsing. 1M-token context that accepts text, image, video, audio and PDF input. Reasons before it acts, at a price low enough to run as a subagent or in high-volume background loops.
▼Muse Ember is somewhat expensive at $0.10/M tokens input and $0.50/M tokens output. Cached input reads are priced at $0.004/M tokens, making repeated context cheaper. The model supports vision/image input, audio input, extended reasoning, a 1M context window.