prices synced 2026-09-11

Muse Glimmer 30B (batch)

Meta · Multimodal · Released Aug 2026

Compare

A 30-billion-parameter dense multimodal model from Meta, distilled from the Muse Spark reasoning series to run efficiently on consumer hardware.

Strengths
Handles both text and images in a single model at a fraction of the parameter count of the Muse Spark series, making it suitable for local deployment and inference on standard GPUs.
Best for
Multimodal tasks on resource-constrained environments where the full Muse Spark models would be impractical, such as edge devices or development machines.
Limitations
Trades reasoning capability and context window size (131K tokens) for efficiency compared to Muse Spark 1.2 and 1.3, which offer 1-million-token context and more advanced reasoning for agentic workflows.

Input / 1M

$0.175

Output / 1M

$0.75

Cached input / 1M

$0.02

Context window

131K

Price history

Input (solid)Output (dashed)
Price per 1M tokens over timeOutput went from $1.50 to $0.75; Input went from $0.35 to $0.175 between Aug 2026 and Sep 2026.$0$0.5$1.00$1.50Output on 29 Aug 2026: $1.50Output on 8 Sep 2026: $0.75Out $0.75Input on 29 Aug 2026: $0.35Input on 8 Sep 2026: $0.175In $0.175Aug 2026Sep 2026

Price change

30d
in decreased 50.0% out decreased 50.0%
90d
in decreased 50.0% out decreased 50.0%
1y
in decreased 50.0% out decreased 50.0%
Since launch
in decreased 50.0% out decreased 50.0%

Snapshots

Effective Input Output Cached in Note Source
8 Sep 2026 $0.175 $0.75 $0.02 Imported from OpenRouter openrouter.ai
29 Aug 2026 $0.35 $1.50 $0.04 Imported from OpenRouter openrouter.ai

More from Meta

Report a problem