Qwen LLM Collection

Qwen × MuleRouter

Get your API key and start using Qwen 3 immediately.
Experience state-of-the-art reasoning and coding capabilities with zero setup.

Complete Catalog

Qwen Collections

Browse the full library of Qwen language, vision, and coding models.

Qwen3 Max

Flagship Qwen3 model for expansive reasoning and extended context windows

Qwen3 Flash

Latency-optimized Qwen3 inference for chat and tool use at scale

Qwen3 Plus

Balanced Qwen3 tier combining strong reasoning with cost efficiency

Chat Playground

Live Demo

Test drive Qwen3-MAX. Experience frontier-class reasoning and coding capabilities in real-time.

Playground

qwen3-max

qwen3-max

Sign in to start chatting.

AI can make mistakes. Verify important information.

Why Qwen?

Frontier Intelligence. Available Everywhere.

Consistently topping global benchmarks in math, coding, and reasoning. Delivering state-of-the-art performance with the unparalleled flexibility of open weights.

World-class performance
with Open Weights

Build Powerful AgentsGive your application agency. Native function calling and web search capabilities allow Qwen to execute complex tasks, not just write about them.

128K

Context

450+

Tokens/Sec

Qwen× MuleRouter

terminal

Model Families

Engineered for Scale

Whether you need extreme speed or maximum intelligence, the Qwen3 series offers a precise fit for your production requirements.

Qwen3 Flagship Series

The pinnacle of the Qwen lineup. Featuring massive 1M+ context windows and SOTA performance across reasoning, coding, and math benchmarks.