A
Qwen3 235B A22B Instruct 2507OPEN
Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass.
Prices update automatically — checked daily against provider list prices.
- $0.16 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 66% of the 191 open-weight models tracked here
- 9 of 51 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 235B A22B Instruct 2507, measured by Artificial Analysis. Higher is better.
For the same budget, Qwen3 235B A22B Instruct 2507 delivers 7.3 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.91 per 1M tokens (median of 22) — this one costs $0.16.
Cheaper and better on this index: GLM 5.3 Flash · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 and 12 more
About this model
Qwen3 235B A22B Instruct 2507 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 235B A22B Instruct 2507?
Qwen3 235B A22B Instruct 2507 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 18.4 on the Artificial Analysis intelligence index.
Is Qwen3 235B A22B Instruct 2507 free?
The weights are free and open — you can self-host Qwen3 235B A22B Instruct 2507 and pay nothing per token. If you prefer a hosted API, list prices are $0.09 per million input tokens and $0.35 per million output tokens.
What is Qwen3 235B A22B Instruct 2507 good at?
Independent benchmarks from Artificial Analysis give it GPQA 75.3%, MMLU-Pro 82.8%, Humanity's Last Exam 11.1%, Long Context Reasoning 33%, LiveCodeBench 52.4%, SciCode 36%, MATH-500 98%, AIME 71.7%, AIME 2025 71.7%, IFBench 46.1%, τ²-Bench 33.3%, Terminal-Bench Hard 15.2%. It is particularly used for mathematical reasoning.
Can I self-host Qwen3 235B A22B Instruct 2507?
Yes. Qwen3 235B A22B Instruct 2507 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.