Qwen3 VL 235B A22B Thinking
by Hugging Face · family qwen · listed Sep 2025RTVW
Qwen vision-language model for visual reasoning, documents, and agent tasks
Current rates USD per 1M tokens
Input$0.98
Output$3.95
Cache read—
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3-VL-235B-A22B-Thinking- Context window
- 131K tokens
- Max output
- 33K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Mar 2025
- Released
- 2025-09-23
- Last updated
- 2025-09-23
- Provider docs
- huggingface.co/docs/inference-providers
Back of the envelope
≈
Also listed at
- Merge Gateway$0.287 in · $2.87 out
- OpenRouter$0.40 in · $4.00 out
- Eden AI$0.40 in · $4.00 out
- Kilo Gateway$0.40 in · $4.00 out
- SiliconFlow$0.45 in · $3.50 out
- SiliconFlow (China)$0.45 in · $3.50 out
- NanoGPT$0.50 in · $6.00 out
- Jalapeno Cloud$0.98 in · $3.95 out
- NovitaAI$0.98 in · $3.95 out
- LLM Gateway$0.98 in · $3.95 out