Context
328K
Input
$0.10/M
Output
$0.30/M
Aliases:llama4-scout-17b-instructllama-4-scout-17b-16e-instructllama-scout-4llama4-scoutllama-4-scout-instructllama4-scout-instructllama-scout-4-instruct
Meta's latest Llama 4 model with 17B active parameters using mixture-of-experts architecture.
deepinfra/llama-4-scoutQuantfp8
- Input
- $0.10/M
- Output
- $0.30/M
- Context
- 328K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.30/M