qwen
Qwen: Qwen3 VL 235B A22B Instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Quality Score
99/100
composite of price, context, capability
Input Price
$0.20
per 1M tokens
Output Price
$0.88
per 1M tokens
Context Window
262,144
tokens
- Model ID
- qwen/qwen3-vl-235b-a22b-instruct
- Vendor
- qwen
- Tokenizer
- Qwen3
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Similar models
qwen
Qwen: Qwen Plus 0728 (thinking)
$0.26 in / $0.78 out
1,000,000 ctx
99
qwen
Qwen: Qwen3.6 35B A3B
$0.16 in / $0.97 out
262,144 ctx
99
qwen
Qwen: Qwen3.5 Plus 2026-04-20
$0.40 in / $2.40 out
1,000,000 ctx
100
qwen
Qwen: Qwen3.6 Flash
$0.25 in / $1.50 out
1,000,000 ctx
100
qwen
Qwen: Qwen3.6 27B
$0.20 in / $1.56 out
262,144 ctx
100
qwen
Qwen: Qwen3.6 Plus
$0.33 in / $1.95 out
1,000,000 ctx
100