Qwen: Qwen3 VL 235B A22B Thinking
qwen/qwen3-vl-235b-a22b-thinking
Qwen3 VL 235B A22B Thinking is an open-weight heavyweight from Qwen — 235B parameters with 22B active per token, ranking #122 of 235 on the TryAii Score. API pricing starts at $0.4/$4 per million input/output tokens, though similar scores now sell for about $1.65 per million output tokens, with 2 independent hosts serving it. It's reasonably quick at roughly 34-54 tokens/sec.
Prompt $/1M
$0.400
Completion $/1M
$4.000
Context
131,072 tok
Best provider
57 tok/s · Alibaba
Specs
- Model id
- qwen/qwen3-vl-235b-a22b-thinking
- Display name
- Qwen: Qwen3 VL 235B A22B Thinking
- Modality
- text+image->text
- Tokenizer
- Qwen3
- Instruct type
- —
- Context length
- 131,072
- Max completion
- 32,768
- Prompt $/1M
- $0.400
- Completion $/1M
- $4.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Alibabafastest | 57 |
| Novita | 52 |
| SiliconFlow | 15 |
| qwenfastest | — |