← All models
Alibaba
Qwen3.8-27B
Live · US + CAtextimageApache 2.0
Dense, natively multimodal workhorse that fits on a single GPU. Passed 1M downloads in two days.
Price per 1M tokens
Input
$0.15
Cached input
—
Output
$1.88
Priced per model · Same in US and CA · Free tier included · Pricing
AA Index
34
#8 of 14
open models we serve
Specs
- Model id
qwen3-8-27b- Weights released
- Aug 14, 2026
- Parameters
- 27.8B
- Architecture
- Dense
- Context
- 256K tokens (262,144)
- Input
- text, image
- License
- Apache 2.0
- Regions
- us, ca
- Weights
- Qwen/Qwen3.8-27B ↗
Benchmarks
- Artificial Analysis Intelligence Index34
- GPQA Diamond89.2%
- SWE-bench Pro61.7%
Sources: huggingface.co · github.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.
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="qwen3-8-27b",
messages=[{"role": "user", "content": "Hello"}],
)