Qwen3 VL 235B A22B Thinking
Qwen3 series VL models feature significantly enhanced multimodal reasoning capabilities, with a particular focus on optimizing the model for STEM and mathematical reasoning.
text + image + file → text · made by Alibaba
Sold by 12 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock 0 ways | $0.53per Mtok in$2.66per Mtok out | |
| AWS Bedrock cloudnot on the seller's list today | standard | $0.53per Mtok in$2.66per Mtok outraw.githubusercontent.com · read 2026-08-27 |
| Fireworks AI aggregator | standard | $0.22per Mtok in$0.88per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Nous Research aggregator | standard | $0.4per Mtok in$4per Mtok outinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 2 ways | $0.4per Mtok in$4per Mtok out | |
| OpenRouter aggregator | standard | $0.4per Mtok in$4per Mtok outopenrouter.ai · read 2026-08-24 |
| OpenRouter aggregator | novita/bf16 | $0.98per Mtok in$3.95per Mtok outopenrouter.ai · read 2026-08-25 |
| Vercel AI Gateway aggregator | standard | $0.4per Mtok in$4per Mtok outai-gateway.vercel.sh · read 2026-08-25 |
| DeepInfra aggregator | standard | $0.45per Mtok in$3.49per Mtok outapi.deepinfra.com · read 2026-08-25 |
| SiliconFlow aggregator | standard | $0.45per Mtok in$3.5per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers 2 ways | $0.98per Mtok in$3.95per Mtok out | |
| Hugging Face Inference Providers aggregator | standard | $0.98per Mtok in$3.95per Mtok outmodels.dev · read 2026-09-16 |
| Hugging Face Inference Providers aggregator | novita | $0.98per Mtok in$3.95per Mtok outrouter.huggingface.co · read 2026-08-25 |
| Novita AI aggregator | standard | $0.98per Mtok in$3.95per Mtok outapi.novita.ai · read 2026-08-25 |
| PPIO aggregator | standard | $2per Mtok in$20per Mtok outapi.ppinfra.com · read 2026-09-10 |
About
Qwen3 VL 235B A22B Thinking — a text model from Alibaba, sold by 9 companies from $0.22 in and $0.88 out per million tokens.
It takes text, images and files and returns text, with a context window of 131,072 tokens. It was published in September 2025, trained on material up to March 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under ocr and reasoning. Nine companies sell it. The cheapest is $0.22 in and $0.88 out per million tokens at Fireworks AI. Beside the standard rate there are separately routed and regional lanes.
Every current figure
- Maker
- Alibaba
- Register
- model
- Takes
- text + image + file
- Returns
- text
- Context
- 131,072 tokens
- Published
- September 2025
- Knowledge to
- March 2025
- Parameters
- 236 billion
- Licence
- not read
- Sellers
- 9
- Maker's own price
- not read
- Price
- $0.22 in and $0.88 out per million tokens — Fireworks AI
Known as 2 names
Qwen/Qwen3-VL-235B-A22B-Thinkingalibaba/qwen3-vl-thinking