Requesty
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.

πŸ‘VisionπŸ”§Tool calling⚑Caching

Pricing per 1M tokens

Input
$0.20
Output
$0.80
Cache write
$0.80
Cache read
$0.20

Specifications

Context window131K tokens
Max output66K tokens
API typechat
AddedJul 31, 2025
Model IDalibaba/qwen3-30b-a3b-instruct-2507

Privacy & data

Data retentionNo
Used for trainingNo
Provider locationπŸ‡ΈπŸ‡¬ Singapore