A
Qwen3 235B A22B Thinking 2507OPEN
Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks.
Prices update automatically — checked daily against provider list prices.
- $1.21 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 11% of the 200 open-weight models tracked here
- 38 of 43 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 235B A22B Thinking 2507, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
About this model
Qwen3 235B A22B Thinking 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 Thinking 2507?
Qwen3 235B A22B Thinking 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.
Is Qwen3 235B A22B Thinking 2507 free?
The weights are free and open — you can self-host Qwen3 235B A22B Thinking 2507 and pay nothing per token. If you prefer a hosted API, list prices are $0.45 per million input tokens and $3.5 per million output tokens.
What is Qwen3 235B A22B Thinking 2507 good at?
Independent benchmarks from Artificial Analysis give it GPQA 79%, MMLU-Pro 84.3%, Humanity's Last Exam 15.9%, Long Context Reasoning 72%, LiveCodeBench 78.8%, SciCode 41.4%, MATH-500 98.4%, AIME 94%, AIME 2025 91%, IFBench 51.2%, τ²-Bench 53.2%, τ-Bench Banking 7.8%, Terminal-Bench 12%, Terminal-Bench Hard 13.6%. It is particularly used for code generation.
Can I self-host Qwen3 235B A22B Thinking 2507?
Yes. Qwen3 235B A22B Thinking 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.