by Alibaba (Qwen Team)

Qwen3 235B A22B Instruct 2507.

text open weights datacenter 235B params 262K ctx
Cheapest input
$0.09/M
on DeepInfra
Cheapest output
$0.55/M
on DeepInfra
Smallest GPU
4× Nvidia Q RTX 8000
$1.08/hr
Context window

How much it can remember.

262K tokens ≈ 196,608 English words
4K 32K 128K 1M
Capabilities

What it can do.

· Vision input
· Audio input
· Video input
· Function calling
· Tool use
· JSON mode
✓ Streaming
· Fine-tuning