AI model · Qwen
Qwen3 Max Thinking
Model ID: qwen/qwen3-max-thinking
- Input
- $0.78 per 1M tokens
- Output
- $3.90 per 1M tokens
- Context
- 262K tokens at once
- Max output
- 66K tokens per reply
- Released
- 9 Feb 2026 Qwen
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- NoOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...
Sources
- Qwen: Qwen3 Max Thinking on OpenRouter — read 2 Oct 2026