A
Qwen3.6 35B A3BOPEN
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token.
Prices update automatically — checked daily against provider list prices.
- $0.31 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 50% of the 200 open-weight models tracked here
- 15 of 43 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3.6 35B A3B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
About this model
Qwen3.6 35B A3B 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 Qwen3.6 35B A3B?
Qwen3.6 35B A3B 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 Qwen3.6 35B A3B free?
The weights are free and open — you can self-host Qwen3.6 35B A3B and pay nothing per token. If you prefer a hosted API, list prices are $0.1 per million input tokens and $0.95 per million output tokens.
What is Qwen3.6 35B A3B good at?
Independent benchmarks from Artificial Analysis give it GPQA 84.1%, Humanity's Last Exam 22.2%, Long Context Reasoning 71.7%, SciCode 36.6%, IFBench 64.4%, τ²-Bench 95.3%, τ-Bench Banking 9.3%, Terminal-Bench 44.9%, Terminal-Bench Hard 34.8%. It is particularly used for code generation.
How fast is Qwen3.6 35B A3B?
It generates about 143.8 tokens per second, with a median 1.08s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Qwen3.6 35B A3B?
Yes. Qwen3.6 35B A3B 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.