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.

ChatQwen82k tokens$0.218 / $2.6161 · 1M

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

Context
82k tokens
Completion cap
32,768
Tools
Yes
JSON
Yes
Released
2025-08-28

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-30b-a3b-thinking-2507",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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. Qwen3 30B A3B Thinking 2507 runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3-30b-a3b-thinking-2507.
Is Qwen3 30B A3B Thinking 2507 free?
No. Input is $0.218 per 1M tokens and output is $2.6161 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen3 30B A3B Thinking 2507?
Qwen3 30B A3B Thinking 2507 has a 82k tokens context window. It supports up to 32,768 completion tokens.
Does Qwen3 30B A3B Thinking 2507 support tool calling and structured outputs?
Qwen3 30B A3B Thinking 2507 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen3 30B A3B Thinking 2507 released?
Qwen3 30B A3B Thinking 2507 was released on 2025-08-28.

More models from Qwen