A
Qwen3.7 MaxOPEN
Qwen3.7 Max (Alibaba): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.
Prices update automatically — checked hourly against provider list prices.
Benchmarks & performance
Independent benchmark scores for Qwen3.7 Max, measured by Artificial Analysis. Higher is better.
For the same budget, Qwen3.7 Max delivers 2 times more capability. Open weights also mean you can self-host it and pay nothing per token.
About this model
Qwen3.7 Max 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 hourly, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Qwen3.7 Max?
Qwen3.7 Max 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 46 on the Artificial Analysis intelligence index.
Is Qwen3.7 Max free?
The weights are free and open — you can self-host Qwen3.7 Max and pay nothing per token. If you prefer a hosted API, list prices are $1.48 per million input tokens and $4.43 per million output tokens.
What is Qwen3.7 Max good at?
Independent benchmarks from Artificial Analysis give it GPQA 92.3%, Humanity's Last Exam 38.1%, Long Context Reasoning 69%, SciCode 48.8%, IFBench 80.5%, τ²-Bench 94.7%, τ-Bench Banking 10.9%, Terminal-Bench 74.5%, Terminal-Bench Hard 50.8%. It is particularly used for code generation.
How fast is Qwen3.7 Max?
It generates about 201.5 tokens per second, with a median 1.59s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Qwen3.7 Max?
Yes. Qwen3.7 Max 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.