Back to models
available
Qwen 4 Max Thinking
qwen/qwen4-max:thinkingPrices
- Input
$1.41 per 1M tokens
low- Input (cache write)
$1.77 per 1M tokens
low- Input (cached read)
$0.071 per 1M tokens
low- Output
$4.24 per 1M tokens
low
Specifications
- Provider
- qwen
- Context window
- 1,000,000
- Max output tokens
- 262,144
- Open weights
- no
- Released
- 11/16/2026
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 1.41 per 1M tokens, unchanged since 11/17/2026
- Output
- 4.24 per 1M tokens, unchanged since 11/17/2026
- Input (cached read)
- 0.071 per 1M tokens, unchanged since 11/17/2026
- Input (cache write)
- 1.77 per 1M tokens, unchanged since 11/17/2026