---
id: "qwen/qwen3-vl-235b-a22b-thinking"
also: ["qwen/qwen3-vl-235b-a22b-thinking", "Qwen/Qwen3-VL-235B-A22B-Thinking", "hf/Qwen/Qwen3-VL-235B-A22B-Thinking"]
cheapest_list_usd_per_m: "0.4 in, 4.0 out, at alibaba on openrouter"
cheapest_effective_usd_per_m: "0.3999 in, 4.0 out, at alibaba on openrouter"
context: 131072
max_output: 32768
input: ["text", "image"]
output: ["text"]
released: "2025-09-23"
params: ["frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 4
gateways: "hf (2), openrouter (2)"
no_training: 2
trains: 0
retains_prompts: 1
intelligence: 13.4000
---
# Qwen: 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....