Skip to main content
Alibaba’s Qwen family covers chat, code generation, vision understanding, and text-to-speech: all available through the Runcrate API with a single API key.

Available Qwen models


Chat: Qwen3 235B Instruct


Code: Qwen3-Coder

Purpose-built for code generation with 256K context:

Vision: Qwen3-VL

Analyze images, extract text, understand diagrams:

TTS: Qwen3 TTS


Choosing the right Qwen model


Tips

  • Qwen3 235B Instruct is the safe default for most chat tasks.
  • Qwen3.5 MoE activates only 17B params per token: use it when you need speed at scale.
  • Qwen3-Coder handles 256K context for cross-file refactoring.
  • Qwen3-VL supports multiple images in a single request.

Next steps