Muse Glimmer 30B is a multimodal chat model from Meta, accepting text and image input and returning text output. It supports a 131,072-token context window, suitable for long documents, codebases and multi-turn conversations that need to retain a large amount of context.
The model supports reasoning, streaming responses, structured outputs and function/tool calling, along with vision (image understanding), making it suitable for agentic and research-oriented applications.
Released August 10, 2026.
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Muse Glimmer 30B is documented as suited to local AI agents that perform multi-step planning, sequential tool invocation, failure recovery, and long-horizon task execution. It is also suited to coding agents for writing, debugging, and resolving real-world software engineering tasks. It is documented for multimodal reasoning, including interpreting screenshots, charts, documents, and images alongside conversation. It is also suited to LLM-as-a-judge evaluation, serving as an evaluator for other models’ outputs.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "meta/muse-glimmer-30b", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "meta/muse-glimmer-30b", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"meta/muse-glimmer-30b","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Muse Glimmer 30B This page | Multimodal reasoning and tool use | |||
| Complex agentic coding and enterprise workflows | ||||
| Reasoning + agents | ||||
| Reasoning + agents | ||||
| Long-context, multimodal & agentic workflows |
Muse Glimmer 30B has a 131,072 tokens context window.
Muse Glimmer 30B takes image, text as input and returns text.
Use meta/muse-glimmer-30b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Muse Glimmer 30B became available on August 10, 2026.
Muse Glimmer 30B is priced at input $0.48139 / 1M tokens, output $2.0631 / 1M tokens, cached input $0.055016 / 1M tokens.
Yes, Muse Glimmer 30B can stream responses as they are generated.
Yes, Muse Glimmer 30B accepts image input alongside text.
Muse Glimmer 30B was built by Meta.
Yes, it supports function calling with parallel tool calls, and includes a reasoning feature.
Yes, it supports structured outputs as one of its listed features.
