Qwen
Models published by Qwen, available through the AnyRouter API. Each can route across multiple upstream providers for availability and price.
Alibaba's specialized coding model with 32B parameters, excelling at code generation, completion, and debugging across 92 programming languages.
Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support.
Alibaba's efficient Mixture-of-Experts model with 30B total parameters and only 3B activated per token, optimized for fast inference.
Qwen3 embedding model for text embedding and ranking tasks.
Qwen3 8B embedding model for text embedding tasks with a 32,768 token context window.
Alibaba's Qwen 3.5 is a 397B-parameter mixture-of-experts model with 17B active parameters, offering strong reasoning capabilities with efficient inference.
Qwen3.5 Plus is Alibaba's mid-tier "plus" model from the Qwen3.5 generation, with a 256K context window and strong reasoning, coding, and tool use.
Qwen3.6 Plus is Alibaba's "plus" model from the Qwen3.6 generation with multimodal (text + image) support, a 1 million token context window, and strong reasoning, coding, and tool use.
Qwen3.7 Max is Alibaba's flagship "max" tier from the Qwen3.7 generation with multimodal (text + image) support, a 1 million token context window, and top-tier reasoning, coding, and tool use.
Qwen3.7 Plus is Alibaba's advanced multimodal model with text and image input support, a 1 million token context window, and strong reasoning capabilities. Available through OpenRouter with a user-owned API key (BYOK).
Alibaba's QwQ 32B reasoning model with deep chain-of-thought capabilities and strong math and coding performance.