Muse Glimmer 30B

muse-glimmer-30b · Meta

Muse Glimmer 30B is a dense causal language model distilled from Muse Spark, designed for autonomous agent work. It combines multi-step reasoning, robust pattern-based tool invocation, and fault-recovery capabilities, and offers multimodal understanding via a ViT-G/14 perceptual encoder of roughly 1.8 billion parameters, supporting interleaved text and image inputs, a context window of over 131K tokens, and optional inference strength settings (from low to ultra-high). Muse Glimmer is trained on data in over 100 languages, performs strongly for its size on agent benchmarks including MCP Atlas, DeepSearch QA, Gaia2, and SWE-Bench Pro, and is released under the Apache 2.0 license.

API Pricing

Input$0.35 / 1M tokens
Output$1.5 / 1M tokens
Cache read$0.04 / 1M tokens

Specifications

Context131K tokens
Modalitiestext, image
Featuresthinking, tool calling

Frequently asked questions

What is muse-glimmer-30b?

Muse Glimmer 30B is a dense causal language model distilled from Muse Spark, designed for autonomous agent work. It combines multi-step reasoning, robust pattern-based tool invocation, and fault-recovery capabilities, and offers multimodal understanding via a ViT-G/14 perceptual encoder of roughly 1.8 billion parameters, supporting interleaved text and image inputs, a context window of over 131K tokens, and optional inference strength settings (from low to ultra-high). Muse Glimmer is trained on data in over 100 languages, performs strongly for its size on agent benchmarks including MCP Atlas, DeepSearch QA, Gaia2, and SWE-Bench Pro, and is released under the Apache 2.0 license.

What is the context length of muse-glimmer-30b?

muse-glimmer-30b has a 131,000 token context window.

How much does muse-glimmer-30b cost?

On AIHubMix, muse-glimmer-30b costs $0.35 per million input tokens and $1.5 per million output tokens. Cached input reads are billed at $0.04 per million tokens.

What modalities does muse-glimmer-30b support?

muse-glimmer-30b accepts text and image input.

What capabilities does muse-glimmer-30b support?

muse-glimmer-30b supports thinking and tool calling. Per-protocol parameter support is listed in the capability table on this page.

How do I call muse-glimmer-30b via API?

muse-glimmer-30b is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to muse-glimmer-30b — no other code changes needed.

Who created muse-glimmer-30b?

muse-glimmer-30b is developed by Meta. AIHubMix aggregates it alongside models from other providers behind one API and one bill.

More models from Meta

muse-spark-1.2

by Meta

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It…

$1.375/1M in · $4.675/1M out
1,000,000 tokens context

muse-spark-1.1

by Meta

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It…

$1.375/1M in · $4.675/1M out
1,000,000 tokens context

Gryphe/MythoMax-L2-13b

by Meta
$0.4/1M in · $0.4/1M out

WizardLM/WizardCoder-Python-34B-V1.0

by Meta
$0.9/1M in · $0.9/1M out

aihubmix-Llama-3-1-405B-Instruct

by Meta
$5/1M in · $15/1M out

aihubmix-Llama-3-1-70B-Instruct

by Meta
$0.6/1M in · $0.78/1M out

Use muse-glimmer-30b via the AIHubMix unified API — one interface for every major LLM.