Back to models
available
Llama 3.1 8B (decentralized)
nano-gpt/meta-llama-3-1-8b-instruct-fp8Prices
- Input
$0.02 per 1M tokens
low- Input (cached read)
$0.01 per 1M tokens
low- Output
$0.03 per 1M tokens
low
Specifications
- Provider
- nano-gpt
- Context window
- 128,000
- Max output tokens
- 16,384
- Open weights
- yes
- Released
- 01/01/2024
- Retires
- no date announced
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.02 per 1M tokens, unchanged since 09/14/2026
- Output
- 0.03 per 1M tokens, unchanged since 09/14/2026
- Input (cached read)
- 0.01 per 1M tokens, unchanged since 09/14/2026