Qwen: Qwen3 30B A3B Thinking 2507

QwenID: qwen/qwen3-30b-a3b-thinking-2507

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated from final answers. Compared to earlier Qwen3-30B releases, this version improves performance across logical reasoning, mathematics, science, coding, and multilingual benchmarks. It also demonstrates stronger instruction following, tool use, and alignment with human preferences. With higher reasoning efficiency and extended output budgets, it is best suited for advanced research, competitive problem solving, and agentic applications requiring structured long-context reasoning.

Pricing per 1M Tokens

Input (Prompt)$0.08
Output (Completion)$0.40
Cache Read$0.08
Cache WriteFree
ImageN/A

Specifications

Context Length131K
Max Output Tokens131K
Input ModalitiesText
Output ModalitiesText
TokenizerQwen3
Instruct TypeN/A
Top Provider Context131K
Top Provider Max Output131K
ModeratedNo

Compare this model

See how Qwen: Qwen3 30B A3B Thinking 2507 stacks up against other models.

vs Qwen: Qwen3.5-27Bvs Qwen: Qwen3.5-9Bvs Qwen: Qwen3.5-35B-A3Bvs Qwen: Qwen3.5-122B-A10Bvs Qwen: Qwen3.5-Flash

More from Qwen

Qwen: Qwen3.5-27B
Input$0.20
Context262K
Qwen: Qwen3.5-9B
Input$0.05
Context256K
Qwen: Qwen3.5-35B-A3B
Input$0.16
Context262K
Qwen: Qwen3.5-122B-A10B
Input$0.26
Context262K
Qwen: Qwen3.5-Flash
Input$0.07
Context1M

Last updated: March 23, 2026

First tracked: March 23, 2026