Qwen

Qwen: Qwen3 235B A22B

qwen/qwen3-235b-a22b

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass.

  • Context window: 131,072 tokens
  • Input: text
  • Output: text
  • Pricing: $0.455/M input tokens, $1.82/M output tokens

RuntimeWire coverage

  • AI agents can copy themselves and spread through networks, researchers find

View on OpenRouter. Model data sourced from OpenRouter.

More models from Qwen

  • Qwen: Qwen3.8 Max (0902)
  • Qwen: Qwen3.8 Flash
  • Qwen: Qwen3.8 27B
  • Qwen: Qwen3.8 27B (free)
  • Qwen: Qwen3.8 2.4T A95B (batch)
  • Qwen: Qwen3.8 2.4T A95B

Browse all AI models