A
Qwen3 Coder 30B A3B InstructOPEN
Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-scale understanding, and agentic tool use.
Prices update automatically — checked daily against provider list prices.
- $0.12 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 74% of the 191 open-weight models tracked here
- 5 of 51 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 Coder 30B A3B Instruct, measured by Artificial Analysis. Higher is better.
For the same budget, Qwen3 Coder 30B A3B Instruct delivers 2.4 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.63 per 1M tokens (median of 18) — this one costs $0.12.
Cheaper and better on this index: GLM 5.3 Flash · DeepSeek V4 Flash 0731 · DeepSeek V4 Flash 0423 and 8 more
About this model
Qwen3 Coder 30B A3B Instruct 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 30B A3B Instruct?
Qwen3 Coder 30B A3B Instruct 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 13.6 on the Artificial Analysis intelligence index.
Is Qwen3 Coder 30B A3B Instruct free?
The weights are free and open — you can self-host Qwen3 Coder 30B A3B Instruct and pay nothing per token. If you prefer a hosted API, list prices are $0.07 per million input tokens and $0.28 per million output tokens.
What is Qwen3 Coder 30B A3B Instruct good at?
Independent benchmarks from Artificial Analysis give it GPQA 51.6%, MMLU-Pro 70.6%, Humanity's Last Exam 3.8%, Long Context Reasoning 31.7%, LiveCodeBench 40.3%, SciCode 27.8%, MATH-500 89.3%, AIME 29.7%, AIME 2025 29%, IFBench 32.7%, τ²-Bench 34.5%, Terminal-Bench Hard 15.2%. It is particularly used for mathematical reasoning.
Can I self-host Qwen3 Coder 30B A3B Instruct?
Yes. Qwen3 Coder 30B A3B Instruct 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.