The Orchestrator › Models › Meta
Meta: Muse Glimmer 30B
Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon...
Specifications
| Provider | Meta |
| Model ID | meta/muse-glimmer-30b |
| Context window | 131K tokens (131,072) |
| Modalities | text + image → text |
| Tokenizer | Other |
| Router sources | OpenRouter, Vercel AI Gateway |
| Released | 2026-08-09 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | meta/muse-glimmer-30b | $0.3 | $1.20 | 131K |
| batch | OpenRouter | meta/muse-glimmer-30b:batch | $0.24 | $0.96 | 131K |
| standard | Vercel AI Gateway | meta/muse-glimmer-30b | $0.35 | $1.50 | 131K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.35 | $1.50 | 131K |
| 2026-11-14 | $0.3 | $1.20 | 131K |
Capabilities
Vision (image input)Agentic tool useStructured outputsReasoning (always on)Controllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p