Qwen: Qwen3 30B A3B Thinking 2507

Qwen: Qwen3 30B A3B Thinking 2507

qwen · Released Aug 28, 2025
35
Our Score

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.

$0.05 / 1M Input Price
$0.34 / 1M Output Price
32,768 tokens Context Window
30B Parameters

Capabilities

Tool Use Function Calling

Architecture

ModalityText → Text
TokenizerQwen3
Parameters30B

Model Information

OpenRouter ID qwen/qwen3-30b-a3b-thinking-2507
Providerqwen
Release Date August 28, 2025
Context Length32,768 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.05 $0.000051
Output $0.34 $0.000340

Live Performance

Live endpoint metrics — refreshed every 30 minutes.

100%
Avg Uptime
272ms
Best Latency (TTFT)
126.5 tok/s
Best Throughput
2/5
Active Endpoints
Available via: Cloudflare, AtlasCloud, SiliconFlow, Nebius, Alibaba