---
id: "meta/muse-glimmer-30b"
also: ["meta/muse-glimmer-30b-20260810", "meta-models/Muse-Glimmer-30B", "hf/meta-models/Muse-Glimmer-30B", "requesty/meta/muse-glimmer-30b", "vercel/meta/muse-glimmer-30b"]
cheapest_list_usd_per_m: "0.3 in, 1.2 out, at deepinfra on hf"
cheapest_effective_usd_per_m: "0.0604 in, 1.099 out, at phala on openrouter"
context: 131072
max_output: 16384
input: ["text", "image"]
output: ["text"]
released: "2026-08-09"
reasoning: ["xhigh", "high", "medium", "low"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 15
gateways: "openrouter (5), hf (4), vercel (4), requesty (2)"
no_training: 10
trains: 1
retains_prompts: 1
intelligence: 6.3000
coding: 49
agentic: 8.5000
---
# Meta: Muse Glimmer 30B

Meta Muse Glimmer 30B is a 30B parameter multimodal model from Meta accepting text and image input and returning text output, with a 131K token context window. Supports chain of thought reasoning and function calling, suited to multimodal question answering, document and image understanding, and agentic workflows. Open weights.