Qwen3 VL 235B A22B Thinking

Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning. Beyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents.

ChatQwen131k tokens$0.436 / $4.3602 · 1M

qwen/qwen3-vl-235b-a22b-thinking

Context
131k tokens
Completion cap
32,768
Tools
Yes
JSON
Yes
Released
2025-09-23

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-vl-235b-a22b-thinking",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Qwen3 VL 235B A22B Thinking?
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math. The series emphasizes robust perception (recognition of diverse real-world and synthetic categories), spatial understanding (2D/3D grounding), and long-form visual comprehension, with competitive results on public multimodal benchmarks for both perception and reasoning. Beyond analysis, Qwen3-VL supports agentic interaction and tool use: it can follow complex instructions over multi-image, multi-turn dialogues; align text to video timelines for precise temporal queries; and operate GUI elements for automation tasks. The models also enable visual coding workflows, turning sketches or mockups into code and assisting with UI debugging, while maintaining strong text-only performance comparable to the flagship Qwen3 language models. This makes Qwen3-VL suitable for production scenarios spanning document AI, multilingual OCR, software/UI assistance, spatial/embodied tasks, and research on vision-language agents. Qwen3 VL 235B A22B Thinking runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3-vl-235b-a22b-thinking.
Is Qwen3 VL 235B A22B Thinking free?
No. Input is $0.436 per 1M tokens and output is $4.3602 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen3 VL 235B A22B Thinking?
Qwen3 VL 235B A22B Thinking has a 131k tokens context window. It supports up to 32,768 completion tokens.
Does Qwen3 VL 235B A22B Thinking support tool calling and structured outputs?
Qwen3 VL 235B A22B Thinking accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen3 VL 235B A22B Thinking released?
Qwen3 VL 235B A22B Thinking was released on 2025-09-23.

More models from Qwen