Alibaba Cloud
qwen3-30b-a3b-instruct-2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and agentic tool use. Post-trained on instruction data, it demonstrates competitive performance across reasoning (AIME, ZebraLogic), coding (MultiPL-E, LiveCodeBench), and alignment (IFEval, WritingBench) benchmarks. It outperforms its non-instruct variant on subjective and open-ended tasks while retaining strong factual and coding performance.
Vision Support
Caching Support
Pricing
$0.2
Input tokens per million
$0.8
Output tokens per million
Caching Pricing
$0.8
Cache write per million
$0.2
Cache read per million
Technical Specifications
Context Window
131K tokens
Max Output Tokens
66K tokens
Global Availability
Last Updated
N/A