Muse Glimmer on FlexAI

Muse · AI at Meta

Serverless
Open Source

Last refreshed 2026-11-18. Next refresh: weekly.

Why use Muse Glimmer on FlexAI?

FlexAI offers Muse Glimmer with pay-as-you-go pricing at $0.35/1M input tokens. FlexAI operates Token Factory, an OpenAI-compatible inference API for open models, plus dedicated GPU endpoints, fine-tuning, training, and private-cloud AI Factory deployments.

Compare Muse Glimmer across 2 providers to find the best fit for your use case
Input / 1M
$0.35
Output / 1M
$1.50
Cache
read $0.040
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: Muse-Glimmer-30B
Model ID
Muse-Glimmer-30B

Request example

Curated snippets for this provider are not sourced yet. Use FlexAI documentation with model ID Muse-Glimmer-30B.

Gotchas

  • Use provider model ID "Muse-Glimmer-30B", not the LLMReference slug "muse-glimmer".

Compare Muse Glimmer Across Providers

ProviderInput (per 1M)Output (per 1M)
OpenRouter$0.30$1.10
FlexAI$0.35$1.50

Pricing

TypePrice (per 1M)
Input tokens$0.35
Output tokens$1.50

Capabilities

VisionMultimodalReasoningJSON / Tool use

About Muse Glimmer

Muse Glimmer is Meta Superintelligence Labs' 30-billion-parameter open-weight multimodal agentic model for local deployment, released August 10, 2026 under Apache 2.0. Distilled from Muse Spark, it combines a ~2B perception encoder with a ~28B text decoder for tool use, multimodal reasoning, and long-horizon agent workflows on consumer GPUs. Weights are available on Hugging Face at meta-models/Muse-Glimmer-30B. Meta's technical report (October 19, 2026) describes it as a dense causal transformer with about 29.6B total parameters (about 1.8B in the frozen perception encoder), a 128K+ context window and four reasoning strengths (low, medium, high, xhigh).

Get Started

Model Specs

Released2026-08-10
Parameters30B
Context128K
ArchitectureDecoder Only
Knowledge cutoff2026-01

Provider

FlexAI

FlexAI Systems Inc

All models on FlexAI →