AI model · Qwen
Qwen3 235B A22B Thinking 2507
Model ID: qwen/qwen3-235b-a22b-thinking-2507
- Input
- $0.23 per 1M tokens
- Output
- $2.30 per 1M tokens
- Context
- 131K tokens at once
- Max output
- 118K tokens per reply
- Released
- 25 Jul 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-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...
Sources
- Qwen: Qwen3 235B A22B Thinking 2507 on OpenRouter — read 2 Oct 2026