The Orchestrator › Models › Meta
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,...
Specifications
| Provider | Meta |
| Model ID | meta/muse-ember-1.0 |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text + image + file + audio + video → text |
| Tokenizer | Other |
| Router sources | OpenRouter, Vercel AI Gateway, Cloudflare |
| Released | 2026-11-09 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| alias | OpenRouter | meta/muse-ember | $0.1 | $0.5 | 1.0M |
| alias | Vercel AI Gateway | meta/muse-ember | $0.1 | $0.5 | 1.0M |
| standard | Cloudflare | meta/muse-ember-1.0 | $0.1 | $0.5 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.1 | $0.5 | — |
Capabilities
Vision (image input)Audio inputVideo inputFile inputAgentic tool useStructured outputsReasoning (always on)1M+ context windowControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
include_reasoning, max_tokens, reasoning, reasoning_effort, repetition_penalty, response_format, seed, structured_outputs, temperature, tool_choice, tools, top_k, top_p