Context
131K
Input
$0.10/M
Output
$0.32/M
Aliases:llama-3-3-70b-instructllama33-70bmeta-llama-3.3-70b
Meta's powerful 70B parameter model quantized to FP8 for fast inference. Excellent for complex reasoning and multilingual tasks.
deepinfra/llama-3.3-70b-instructQuantfp8
- Input
- $0.10/M
- Output
- $0.32/M
- Context
- 131K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.32/M
Priority / Fast