Back to models
available
Nvidia Nemotron 70b
nvidia/llama-3-1-nemotron-70b-instruct-hfPrices
- Input
$0.357 per 1M tokens
low- Input (cached read)
$0.1785 per 1M tokens
low- Output
$0.408 per 1M tokens
low
Specifications
- Provider
- nvidia
- Context window
- 16,384
- Max output tokens
- 8,192
- Open weights
- yes
- Released
- 04/15/2025
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.357 per 1M tokens, unchanged since 09/14/2026
- Output
- 0.408 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.1785 per 1M tokens, unchanged since 09/14/2026