All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3 VL 235B A22B Thinking

Qwen vision-language thinking model for visual reasoning, documents, and agent tasks

Model facts

Context window
131K tokens
Maximum output
33K tokens
Cheapest paid input
$0.287 per 1M tokens
Cheapest paid output
$2.87 per 1M tokens
Open weights
yes
Providers
12

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video.

Observed price history

  • 2026-08-24: $0.287 input / $2.87 output per 1M tokens

API providers

  • Merge Gateway — model id qwen/qwen3-vl-235b-a22b-thinking; $0.287 input / $2.87 output per 1M tokens; provider documentation
  • Eden AI — model id qwen/qwen3-vl-235b-a22b-thinking; $0.4 input / $4 output per 1M tokens; provider documentation
  • Kilo Gateway — model id qwen/qwen3-vl-235b-a22b-thinking; $0.4 input / $4 output per 1M tokens; provider documentation
  • OpenRouter — model id qwen/qwen3-vl-235b-a22b-thinking; $0.4 input / $4 output per 1M tokens; provider documentation
  • OrcaRouter — model id qwen/qwen3-vl-235b-a22b-thinking; $0.4 input / $4 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id qwen3-vl-235b-a22b-thinking; $0.98 input / $3.95 output per 1M tokens; provider documentation
  • Hugging Face — model id Qwen/Qwen3-VL-235B-A22B-Thinking; $0.98 input / $3.95 output per 1M tokens; provider documentation
  • Jalapeno Cloud — model id Qwen3-VL-235B-A22B-Thinking; $0.98 input / $3.95 output per 1M tokens; provider documentation
  • LLM Gateway (NovitaAI) — model id novita/qwen3-vl-235b-a22b-thinking; $0.98 input / $3.95 output per 1M tokens; provider documentation
  • NovitaAI — model id qwen/qwen3-vl-235b-a22b-thinking; $0.98 input / $3.95 output per 1M tokens; provider documentation
  • NanoGPT — model id qwen3-vl-235b-a22b-thinking; $0.5 input / $6 output per 1M tokens; provider documentation
  • Arena — model id qwen3-vl-235b-a22b-thinking; not published input / not published output per 1M tokens; provider documentation