Context1.0M
Muse 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, extraction, and long document parsing.
Performance
Latency (p50)—
Throughput (p50)—
Pricing
Input$0.05/M tokens
Output$0.25/M tokens
Cached input$0.002/M tokens
Features
Inputtext, image, audio, file
Outputtext
APIResponses, Chat Completions, Messages