Back to models
available
NVIDIA Nemotron 3 Ultra
venice/nvidia-nemotron-3-ultra-550b-a55bPrices
- Input
$0.625 per 1M tokens
low- Input (cached read)
$0.1875 per 1M tokens
low- Output
$3.13 per 1M tokens
low
Specifications
- Provider
- venice
- Context window
- 256,000
- Max output tokens
- 32,768
- Open weights
- yes
- Released
- 06/04/2026
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.625 per 1M tokens, unchanged since 09/14/2026
- Output
- 3.13 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.1875 per 1M tokens, unchanged since 09/14/2026