A
Qwen3 Coder 480B A35BOPEN
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team.
Prices update automatically — checked daily against provider list prices.
- $0.48 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 36% of the 200 open-weight models tracked here
- 26 of 43 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 Coder 480B A35B, measured by Artificial Analysis. Higher is better.
About this model
Qwen3 Coder 480B A35B 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 Coder 480B A35B?
Qwen3 Coder 480B A35B 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 Coder 480B A35B free?
The weights are free and open — you can self-host Qwen3 Coder 480B A35B and pay nothing per token. If you prefer a hosted API, list prices are $0.3 per million input tokens and $1 per million output tokens.
What is Qwen3 Coder 480B A35B good at?
Independent benchmarks from Artificial Analysis give it GPQA 61.8%, MMLU-Pro 78.8%, Humanity's Last Exam 4.5%, Long Context Reasoning 45.7%, LiveCodeBench 58.5%, MATH-500 94.2%, AIME 47.7%, AIME 2025 39.3%, IFBench 40.5%, τ²-Bench 43.6%, Terminal-Bench Hard 18.9%. It is particularly used for mathematical reasoning.
Can I self-host Qwen3 Coder 480B A35B?
Yes. Qwen3 Coder 480B A35B 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.