ScaledThought
← All models

Meta

Muse Glimmer

Live · US + CAtextimageApache 2.0

Meta's first open-weight release since Llama 4: a dense agent model distilled from Muse Spark, sized for one 24GB GPU.

Price per 1M tokens

Input

$0.35

Cached input

$0.04

Output

$1.50

Priced per model · Same in US and CA · Free tier included · Pricing

AA Index

17

#14 of 14
open models we serve

Specs

Model id
muse-glimmer
Weights released
Aug 10, 2026
Parameters
30B
Architecture
Dense
Context
—
Input
text, image
License
Apache 2.0
Regions
us, ca

Benchmarks

  • Artificial Analysis Intelligence Index17
  • SWE-bench Pro51.2%
  • AIME 202594.7%

Sources: huggingface.co · venturebeat.com · artificialanalysis.ai

Use it

Three lines of code, or zero.

OpenAI-compatible. Use the model id below, or auto to let the router decide when this model is worth it.

Quickstart→
import os
from openai import OpenAI

client = OpenAI(base_url=os.environ["ST_BASE_URL"], api_key=os.environ["ST_API_KEY"])
resp = client.chat.completions.create(
    model="muse-glimmer",
    messages=[{"role": "user", "content": "Hello"}],
)

Opens your agent with the prompt typed. You press Enter.