together_ai

Meta: Muse Glimmer 30B

meta-models/Muse-Glimmer-30B
Context

131K

Input

text, image

Output

text

Tool calling

Supported

About this model

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for local autonomous agentic workflows on consumer hardware. It combines multi-step reasoning, reliable schema-based tool calling, and failure recovery with multimodal understanding via a built-in perception encoder. It supports interleaved text and image input, controllable reasoning strength, and is highly compatible with agentic orchestration frameworks.

Compare Text Models

Input modalities

text

Accepted as model input

image

Accepted as model input

Providers

Available routing options for this model through OneInfer.

together_ai
Available

Input tokens

$0.350 / 1M tokens

Output tokens

$1.500 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.350 / 1M tokens
Output tokens$1.500 / 1M tokens
Cached input tokens$0.040 / 1M tokens

Performance

Published evaluation results associated with this model.

General agentic

MCP Atlas75.5
DeepSearch QA74.6
τ³-Banking23.5
WildClawBench47.6
GDPval-AA953
GAIA243.3
SkillsBench44.3
OSWorld-Verified65.9

Agentic coding

SWE-Bench Pro51.2
SWE-Bench Verified76
TerminalBench 2.151.7
SciCode43.6

Multimodal

Charxiv Reasoning78.8
ScreenSpot Pro75.4
OmniDocBench v1.575.8
MMMU Pro74

General capabilities and reasoning

IFBench77
AIME 202694.7
GPQA Diamond83.5
Humanity's Last Exam22
AA-LCR80
Beam 128K65.1

API example

Refer Documentation
curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-models/Muse-Glimmer-30B",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'