# Qwen: Qwen3 30B A3B Thinking 2507

Provider: qwen  
Category: llm  
Model ID: `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...

## Specs

- Context length: 131072 tokens
- Max output: 131072 tokens
- Modalities: text
- Released: 2025-08-28

## Pricing

- Input: $0.08 per million tokens
- Output: $0.40 per million tokens

## Providers

- **qwen** — ctx 131072, input $0.08/M, output $0.40/M

---
Last verified: 2026-04-23T23:46:29.618Z  
Canonical URL: https://switchy.build/models/qwen3-30b-a3b-thinking-2507