← Back to all models

Qwen/Qwen3-30B-A3B-Instruct-2507

qwen3-30b-a3b-instruct-2507

Provider: SiliconFlow (China), Context: 262000, Output Limit: 262000

Available at 6 Providers

Provider Source Input Price ($/1M) Output Price ($/1M) Description Free
siliconflowcn models-dev Input: $0.09 Output: $0.30 Provider: SiliconFlow (China), Context: 262000, Output Limit: 262000
chutes models-dev Input: $0.08 Output: $0.33 Provider: Chutes, Context: 262144, Output Limit: 262144
siliconflow models-dev Input: $0.09 Output: $0.30 Provider: SiliconFlow, Context: 262000, Output Limit: 262000
modelscope models-dev Input: $0.00 Output: $0.00 Provider: ModelScope, Context: 262144, Output Limit: 16384
fireworksai litellm Input: $0.50 Output: $0.50 Source: fireworks_ai, Context: 262144
openrouter openrouter Input: $0.08 Output: $0.33 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. Context: 262144