Skip to content
LLMs
Meta logo

Meta: Muse Glimmer 30B

by Meta

Meta: Muse Glimmer 30B is a large language model from Meta. It costs $0.350 per million input tokens and $1.50 per million output tokens. Its context window is 131K tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weightsimage input
Input / 1M tokens
$0.350
Output / 1M tokens
$1.50
Cached input / 1M
$0.040

On repeated prefixes

Context window
131K

tokens

Who serves it cheapest

4 hosts serve Muse Glimmer 30B. Same weights, same API - the price difference is pure margin and routing.

Providers serving Meta: Muse Glimmer 30B, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
PhalaCheapest$0.300$1.10131K-95.7%
DeepInfrabf16$0.300$1.20131K-99.8%
Fireworks$0.350$1.50131K-99.8%
Together$0.350$1.50131K-96.7%

The spread between Phala and Together is 1.3× for identical weights. Quantization and context limits differ, so check both columns before switching.

About 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

Meta: Muse Glimmer 30B specifications
Model IDmeta/muse-glimmer-30b
ProviderMeta
Context window131K tokens
Max output118K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff-
Open weightsYes - meta-models/Muse-Glimmer-30B
ReleasedAugust 9, 2026

Cheaper alternatives

Models that cost less than Muse Glimmer 30B while keeping at least half its context window and every input modality it supports.

Frequently asked

How much does Meta: Muse Glimmer 30B cost?

$0.350 per million input tokens and $1.50 per million output tokens. Cached input reads cost $0.040 per million tokens.

What is the context window of Meta: Muse Glimmer 30B?

131K tokens, with up to 118K tokens of output per request.

Which provider serves Meta: Muse Glimmer 30B cheapest?

Phala at $0.300 per million input tokens - 1.3× cheaper than Together, the most expensive of the 4 hosts serving it.