Private AI
Meta's Muse Glimmer 30B is a dense, open-weight multimodal model for long-horizon agentic and coding workflows. Running inside a TEE (Trusted Execution Environment), with provider attestation support.
Added Aug 13, 2026
Model weightsContext Window
131.1K
Max Output
131.1K
Input Price (Auto)
$0.35/1M
Output Price (Auto)
$1.50/1M
Cache Read (Auto)
$0.040/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
35.1
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
49.0
GPQA Diamond
Graduate-level scientific reasoning
83.5%
Better than 77% of models compared
HLE
Humanity's Last Exam
22.0%
Better than 78% of models compared
AA-LCR
Long context reasoning evaluation
80.0%
Better than 99% of models compared
SciCode
Python programming for scientific computing
43.6%
Better than 81% of models compared
Last updated Aug 13, 2026
Artificial Analysis