All AI models · LLM benchmarks · Methodology

Alibaba

Qwen3 VL 235B A22B

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

Model facts

Context window
131K tokens
Maximum output
33K tokens
Cheapest paid input
$0.2 per 1M tokens
Cheapest paid output
$0.88 per 1M tokens
Open weights
yes
Providers
18

Capabilities and modalities

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

Local hardware estimate

At 4K context: Q4_K_M 127.3 GiB, Q8_0 237.0 GiB, F16 442.8 GiB working memory.

Parameters
235.7 billion
Architecture
qwen3vlmoe
Model license
apache-2.0

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning20.9not measured88.3not measured

Observed price history

  • 2026-08-24: $0.2 input / $0.88 output per 1M tokens

API providers

  • Deep Infra — model id Qwen/Qwen3-VL-235B-A22B-Instruct; $0.2 input / $0.88 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id qwen3-vl-235b-a22b-instruct; $0.2 input / $0.88 output per 1M tokens; provider documentation
  • Kilo Gateway — model id qwen/qwen3-vl-235b-a22b-instruct; $0.26 input / $1.04 output per 1M tokens; provider documentation
  • Alibaba (China) — model id qwen3-vl-235b-a22b; $0.287 input / $1.15 output per 1M tokens; provider documentation
  • Merge Gateway — model id qwen/qwen3-vl-235b-a22b-instruct; $0.287 input / $1.15 output per 1M tokens; provider documentation
  • NanoGPT — model id qwen/Qwen3-VL-235B-A22B-Instruct; $0.3 input / $1.2 output per 1M tokens; provider documentation
  • Helicone — model id qwen3-vl-235b-a22b-instruct; $0.3 input / $1.5 output per 1M tokens; provider documentation
  • Hugging Face — model id Qwen/Qwen3-VL-235B-A22B-Instruct; $0.3 input / $1.5 output per 1M tokens; provider documentation
  • Jalapeno Cloud — model id Qwen3-VL-235B-A22B-Instruct; $0.3 input / $1.5 output per 1M tokens; provider documentation
  • NovitaAI — model id qwen/qwen3-vl-235b-a22b-instruct; $0.3 input / $1.5 output per 1M tokens; provider documentation
  • Eden AI — model id qwen/qwen3-vl-235b-a22b-instruct; $0.4 input / $1.6 output per 1M tokens; provider documentation
  • OrcaRouter — model id qwen/qwen3-vl-235b-a22b-instruct; $0.4 input / $1.6 output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id alibaba/qwen3-vl-235b-a22b-instruct; $0.4 input / $1.6 output per 1M tokens; provider documentation
  • OpenRouter — model id qwen/qwen3-vl-235b-a22b-instruct; $0.21 input / $1.9 output per 1M tokens; provider documentation
  • TensorX — model id qwen/qwen3-vl-235b-a22b-instruct; $0.21 input / $1.9 output per 1M tokens; provider documentation
  • Alibaba — model id qwen3-vl-235b-a22b; $0.7 input / $2.8 output per 1M tokens; provider documentation
  • Cortecs — model id qwen3-vl-235b-a22b; $0.617 input / $3.12 output per 1M tokens; provider documentation
  • Arena — model id qwen3-vl-235b-a22b-instruct; not published input / not published output per 1M tokens; provider documentation