ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Meta
Open-Weight Meta · muse-glimmer-30b · Text+Image

Muse Glimmer 30B Official Specifications, Pricing & Benchmarks

Muse Glimmer 30B (muse-glimmer-30b) by Meta, released 2026-08-10, featuring 131,072 context window, 117,964 max output tokens, and Text+Image input.

📋 Muse Glimmer 30B Official API & System Card Specifications

Verified against official Meta developer documentation & pricing

API Model ID: muse-glimmer-30b

1. Identity & Capabilities

API Spec
API Model ID
muse-glimmer-30b
Release Date
2026-08-10
Weight License
Open-Weight (API Spec)
Native Reasoning
✅ Supported
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
131,000 tokens (131K)
Max Output Tokens
117,964 tokens
Input Modalities
Text + Image
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 0.35
Cached Input / 1M
$ 0.04 -89%
Output / 1M Tokens
$ 1.5

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Official Reasoning & Tool Config
temperature=0.7 top_p=0.95 max_tokens=65,536

📊 Muse Glimmer 30B Full Benchmark Scorecard

26 public benchmarks · ranks among 154 models · synced 2026-11-20

⚔️ Compare head-to-head

💻 Coding 8 items

PinchBench #1/4 90.5%

PinchBench evaluates coding agents on real-world agentic coding tasks, measuring both best-case and average performance across complex software engineering scenarios.

SWE-Bench Verified #28/59 76%

A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.

MCP Atlas #18/39 75.5%

MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

Terminal-Bench 2.1 #34/37 51.7%

Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.

SWE-Bench Pro #47/52 51.2%

SWE-Bench Pro is an advanced version of SWE-Bench that evaluates language models on complex, real-world software engineering tasks requiring extended reasoning and multi-step problem solving.

WildClawBench #4/5 47.6%

WildClawBench is an agentic coding benchmark from InternLM/Claw-Eval that reports overall model performance on real-world tool-using development tasks.

SkillsBench #9/11 44.3%

SkillsBench evaluates coding agents on self-contained programming tasks, measuring practical engineering skills across diverse software development scenarios.

SciCode #13/24 43.6%

SciCode is a research coding benchmark curated by scientists that challenges language models to code solutions for scientific problems.

🤖 Agents & Tools 7 items

Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).

Closest Self-Hostable Open-Weight Alternatives to Muse Glimmer 30B

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Muse Glimmer 30B open-source or proprietary?

Muse Glimmer 30B (muse-glimmer-30b) is a proprietary commercial model by Meta. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Muse Glimmer 30B?

Muse Glimmer 30B supports 131K input context and 117,964 max output tokens, priced at $0.35/1M input ($0.04/1M cached) and $1.5/1M output.