ScaledThought
← All models

Alibaba

Qwen3.8-2.4T

Live · US + CAtextApache 2.0

The open checkpoint behind Qwen3.8-Max, the first time Alibaba has released a Max-class model's weights.

Price per 1M tokens

Input

$2.00

Cached input

$0.25

Output

$6.00

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

AA Index

40

#5 of 14
open models we serve

Specs

Model id
qwen3-8-2-4t-a95b
Weights released
Aug 12, 2026
Parameters
2.4T total · 95B active
Architecture
MoE
Context
961K tokens (984,000)
Input
text
License
Apache 2.0
Regions
us, ca

Benchmarks

  • Artificial Analysis Intelligence Index40
  • GPQA Diamond92.6%

Sources: huggingface.co · artificialanalysis.ai · developer.nvidia.com

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="qwen3-8-2-4t-a95b",
    messages=[{"role": "user", "content": "Hello"}],
)

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