Llama 4 Scout 17B 16E Instruct FP8

Meta LlamaText

Llama 4 Scout 17B 16E Instruct FP8 is a text model from Meta Llama with a context window of 10.0M tokens and max output of 4K tokens.

Specifications

Model Keymeta_llama/Llama-4-Scout-17B-16E-Instruct-FP8
ProviderMeta Llama
LiteLLM Providermeta_llama
ModeText
Canonical Namellama-4-scout-17b
Context Window10.0M tokens
Max Output4K tokens

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Pricing

TypePer 1K TokensPer 1M Tokens
Input TokensN/AN/A
Output TokensN/AN/A

Price Comparison by Provider

Compare prices for Llama 4 Scout 17B 16E Instruct FP8 across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price
Output Price
Meta Llamameta_llama/Llama-4-Scout-17B-16E-Instruct-FP8N/AN/A
AWS Bedrockmeta.llama4-scout-17b-instruct-v1:0$0.170$0.660

Similar Models

Models with similar capabilities and context window size.

Model
Provider
Mode
Input Price
Output Price
Context
Max Output
Vision
Functions
Llama 4 Scout 17B 128e Instruct MaasGoogle Vertex AIText$0.250$0.70010.0M10.0Mnoyes
Llama 4 Scout 17B 16E InstructAzure AIText$0.200$0.78010.0M16Kyesyes
Llama 4 Scout 17B 16e Instruct MaasGoogle Vertex AIText$0.250$0.70010.0M10.0Mnoyes