AI model · Qwen
Qwen3 235B A22B
Model ID: qwen/qwen3-235b-a22b
- Input
- $0.46 per 1M tokens
- Output
- $1.82 per 1M tokens
- Context
- 131K tokens at once
- Max output
- 8K tokens per reply
- Released
- 28 Apr 2025 Qwen
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...
Sources
- Qwen: Qwen3 235B A22B on OpenRouter — read 2 Oct 2026