Skip to content
OpenSmartRoute
Model catalogue
Meta

Meta

Muse Glimmer 30B (batch)

meta/muse-glimmer-30b:batch

Specification

Published by the vendor; the platform bills at the target's declared price.

Meta

Muse Glimmer 30B (batch)

reasoning open weights tools

Meta meta/muse-glimmer-30b:batch

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...

Input $/1M
$0.35
Output $/1M
$1.50
Context
131K
Max output
118K
Released
Aug 9, 2026
Modalities
textimage

Cached input reads $0.04 per 1M · weights on Hugging Face as meta-models/Muse-Glimmer-30B

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet
Add a target with metadata.model set to this id.
targets.yamlyaml
# targets.yaml - declare a target that runs Muse Glimmer 30B (batch)
targets:
  - id: muse-glimmer-30b-batch
    kind: llm
    name: Muse Glimmer 30B (batch)
    metadata:
      model: meta/muse-glimmer-30b:batch          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.000925

Price among Meta models

Input list price per million tokens; Muse Glimmer 30B (batch) is the 4th cheapest of 7 listed.