← all models

Qwen3 30B A3B Thinking 2507

qwen · 3B active

openrouter
Parameters 30B openrouter api · from the model id
Context 80K 81920 tokens
Input $0.20 OpenRouter
Output $2.40 OpenRouter
Cache read — OpenRouter

Accepts

text

Capabilities

frequency_penalty include_reasoning max_tokens presence_penalty reasoning response_format seed stop temperature tool_choice tools top_k top_p

Description

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter qwen/qwen3-30b-a3b-thinking-2507 huggingface Qwen/Qwen3-30B-A3B-Thinking-2507 name Qwen: Qwen3 30B A3B Thinking 2507 display name Qwen3 30B A3B Thinking 2507

Identifiers

Vendor
qwen
OpenRouter
qwen/qwen3-30b-a3b-thinking-2507
Hugging Face
Qwen/Qwen3-30B-A3B-Thinking-2507
Active parameters
3B
Released
2025-08-28T16:39:52.000Z
First seen
59 d ago
Last crawled
40 d ago