Context
16K
Input
$0.02/M
Output
$0.05/M
Aliases:llama-3-1-8b-instructllama31-8bmeta-llama-3.1-8b
Meta's efficient 8B parameter model optimized for multilingual dialogue. Fast inference with great performance for everyday tasks.
novita/llama-3.1-8b-instructQuantfp8
- Input
- $0.02/M
- Output
- $0.05/M
- Context
- 16K
- Max out
- 4K
- Caching
- Not offered
- Thinking out
- $0.05/M