A
Qwen3 VL 235B A22B InstructOPEN
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video.
Prices update automatically — checked daily against provider list prices.
- $0.63 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 32% of the 191 open-weight models tracked here
- 31 of 51 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 VL 235B A22B Instruct, measured by Artificial Analysis. Higher is better.
For the same budget, Qwen3 VL 235B A22B Instruct delivers 3.3 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.45 per 1M tokens (median of 19) — this one costs $0.63.
Cheaper and better on this index: GLM 5.3 Flash · Gemini 3.7 Flash (batch) · GPT-5.6 Luna and 59 more
About this model
Qwen3 VL 235B A22B Instruct is an open-weight AI model by Alibaba. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Qwen3 VL 235B A22B Instruct?
Qwen3 VL 235B A22B Instruct is an AI language model from Alibaba. It is open-weight: you can download it and run it on your own hardware, for free. It scores 14.4 on the Artificial Analysis intelligence index.
Is Qwen3 VL 235B A22B Instruct free?
The weights are free and open — you can self-host Qwen3 VL 235B A22B Instruct and pay nothing per token. If you prefer a hosted API, list prices are $0.21 per million input tokens and $1.9 per million output tokens.
What is Qwen3 VL 235B A22B Instruct good at?
Independent benchmarks from Artificial Analysis give it GPQA 71.2%, MMLU-Pro 82.3%, Humanity's Last Exam 6.6%, Long Context Reasoning 32%, LiveCodeBench 59.4%, SciCode 35.9%, AIME 2025 70.7%, IFBench 42.7%, τ²-Bench 35.1%, Terminal-Bench Hard 6.8%. It is particularly used for mathematical reasoning.
Can I self-host Qwen3 VL 235B A22B Instruct?
Yes. Qwen3 VL 235B A22B Instruct has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.