A
Qwen3.8 2.4T A95BOPEN
Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total.
Prices update automatically — checked daily against provider list prices.
- $3 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 3% of the 200 open-weight models tracked here
- 42 of 43 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3.8 2.4T A95B, measured by Artificial Analysis. Higher is better.
About this model
Qwen3.8 2.4T A95B 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 Qwen3.8 2.4T A95B?
Qwen3.8 2.4T A95B 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 Qwen3.8 2.4T A95B free?
The weights are free and open — you can self-host Qwen3.8 2.4T A95B and pay nothing per token. If you prefer a hosted API, list prices are $2 per million input tokens and $6 per million output tokens.
What is Qwen3.8 2.4T A95B good at?
Independent benchmarks from Artificial Analysis give it GPQA 93.5%, Humanity's Last Exam 42.4%, Long Context Reasoning 80.3%, SciCode 54.1%, τ-Bench Banking 49.1%, Terminal-Bench 82%. It is particularly used for code generation.
How fast is Qwen3.8 2.4T A95B?
It generates about 40.2 tokens per second, with a median 2.12s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Qwen3.8 2.4T A95B?
Yes. Qwen3.8 2.4T A95B 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.