Back to models
available
Qwen3.8 2.4T A95B (NVFP4)
inferact/qwen3-8-2-4t-a95b-nvfp4Prices
- Input
$2.00 per 1M tokens
low- Input (cached read)
$0.20 per 1M tokens
low- Output
$6.00 per 1M tokens
low
Specifications
- Provider
- inferact
- Context window
- 262,144
- Max output tokens
- 32,768
- Open weights
- yes
- Released
- 08/12/2026
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 2 per 1M tokens, unchanged since 09/14/2026
- Output
- 6 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.2 per 1M tokens, unchanged since 09/14/2026