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.
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.
muse-glimmer-30b has a 131,000 token context window.
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.
muse-glimmer-30b accepts text and image input.
muse-glimmer-30b supports thinking and tool calling. Per-protocol parameter support is listed in the capability table on this page.
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.
muse-glimmer-30b is developed by Meta. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It…
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It…
Use muse-glimmer-30b via the AIHubMix unified API — one interface for every major LLM.