Back to models
available
Llama-3.3-70B-Instruct
nvidia/llama-3-3-70b-instruct-fp8Prices
- Input
$1.15 per 1M tokens
low- Output
$1.15 per 1M tokens
low
Specifications
- Provider
- nvidia
- Context window
- 128,000
- Max output tokens
- 4,096
- Open weights
- yes
- Released
- 12/06/2024
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 1.15 per 1M tokens, unchanged since 09/14/2026
- Output
- 1.15 per 1M tokens, unchanged since 09/14/2026