Skip to content
Dashboard

Qwen 3 VL 235B A22B Instruct

Qwen 3 VL 235B A22B Instruct is Alibaba Cloud's 235B mixture-of-experts vision-language model with 22B active parameters per token, supporting interleaved text, images, and video over a context window of 262.1K tokens for visual coding, spatial perception, and fine-grained visual understanding. Your use subject to Alibaba Cloud's Terms & Privacy Policies.

Tool UseVision (Image)
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'alibaba/qwen3-vl-235b-a22b-instruct',
prompt: 'Why is the sky blue?'
})

More models by Alibaba Cloud

Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Release Date
1M
2.7s
448tps
$0.32/M
$1.28/M
Read:$0.08/M
Write:$0.5/M
+2
alibaba logo
fireworks logo
togetherai logo
06/02/2026
991K
2.7s
55tps
$2.50/M
$7.50/M
Read:$0.5/M
Write:$3.13/M
alibaba logo
05/21/2026
240K
2.2s
115tps
$1.30/M
$7.80/M
Read:
$0.26/M
Write:
$1.63/M
alibaba logo
04/20/2026
1M
1.7s
110tps
$0.50/M
$3/M
Read:
$0.1/M
Write:
$0.63/M
+1
alibaba logo
togetherai logo
04/02/2026
1M
1.0s
254tps
$0.10/M
$0.40/M
Read:$0.0/M
Write:$0.13/M
+1
alibaba logo
02/24/2026
256K
0.5s
146tps
$0.50/M
$1.20/M
bedrock logo
togetherai logo
07/22/2025