Alibaba

AQwen3 30B A3BOPEN

Qwen3 30B A3B (Alibaba): live API pricing, context window and the best open-source alternatives, tracked daily by olud.ai.

Context window
131K
tokens
Input price
$0.12
per M tokens
Output price
$0.5
per M tokens
Provider
Alibaba

Prices update automatically — checked hourly against provider list prices.

See model comparisons → Compare all model prices

Benchmarks & performance

Independent benchmark scores for Qwen3 30B A3B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.

More intelligence per dollar than Claude Opus 5 (Fast).
For the same budget, Qwen3 30B A3B delivers 2 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Intelligence index9.3
Math index72.3
GPQA61.6%
MMLU-Pro77.7%
Humanity's Last Exam6.6%
Long Context Reasoning0%
LiveCodeBench50.6%
SciCode28.5%
MATH-50095.9%
AIME75.3%
AIME 202572.3%
IFBench41.5%
τ²-Bench26%
Terminal-Bench Hard2.3%
💰 Blended price$0.75 / 1M tokens
📈 Value12.4 intelligence points per $
Benchmark data by Artificial Analysis

About this model

Qwen3 30B 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 hourly, for when you prefer convenience over self-hosting.

Frequently asked questions

What is Qwen3 30B A3B?

Qwen3 30B 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. It scores 9.3 on the Artificial Analysis intelligence index.

Is Qwen3 30B A3B free?

The weights are free and open — you can self-host Qwen3 30B A3B and pay nothing per token. If you prefer a hosted API, list prices are $0.12 per million input tokens and $0.5 per million output tokens.

What is Qwen3 30B A3B good at?

Independent benchmarks from Artificial Analysis give it GPQA 61.6%, MMLU-Pro 77.7%, Humanity's Last Exam 6.6%, Long Context Reasoning 0%, LiveCodeBench 50.6%, SciCode 28.5%, MATH-500 95.9%, AIME 75.3%, AIME 2025 72.3%, IFBench 41.5%, τ²-Bench 26%, Terminal-Bench Hard 2.3%. It is particularly used for mathematical reasoning.

Can I self-host Qwen3 30B A3B?

Yes. Qwen3 30B 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.

Related models

Qwen3.6 PlusAlibabaQwen3.7 PlusAlibabaQwen3.7 MaxAlibabaQwen3.5-FlashAlibabaQwen3.6 35B A3BAlibabaQwen3 235B A22B Instruct 2507Alibaba