Meta: Muse Ember

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,...

muse-ember

Open in chat

List pricing

—

Input: $0.09999999999999999 / 1,000,000 tokens
Output: $0.5 / 1,000,000 tokens
Cache read: $0.004 / 1,000,000 tokens
Cache write: $0.125 / 1,000,000 tokens

How pricing works

Discount history

No discount history yet.

Model details

Input: text, image, video, file, audio
Output: text
Context window: 1,048,576 tokens
Maximum output: 524,288 tokens
Availability: Unknown
Updated: 11/9/2026, 8:47:26 PM UTC

Capacity is reserved when your request is accepted.

Capabilities

ChatStreamingWeb searchVisionTool callingReasoningJSON mode

Supported parameters

include_reasoningmax_tokensreasoningreasoning_effortrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p