Llama 4 Scout 17B 16E Instruct
Llama 4 Scout 17B 16E Instruct is a natively multimodal Mixture of Experts (MoE) model with a context window of 131.1K tokens, purpose-built for processing entire codebases, multi-document corpora, and extended user activity logs in a single inference call.
Tool UseVision (Image)
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'meta/llama-4-scout', prompt: 'Why is the sky blue?'})More models by Meta
| Model |
|---|
| 1M | 3.9s | 205tps | $1.25/M | $4.25/M | Read:$0.15/M Write:— | — | +2 |  | 07/09/2026 | |||
| 131K | 0.2s | 37tps | $0.24/M | $0.97/M | — |   | 04/05/2025 | |||||
| 128K | 0.2s | 156tps | $0.59/M | $0.72/M | — |  | 12/06/2024 | |||||
| 131K | 0.2s | 173tps | $0.02/M | $0.05/M | Read:$0.03/M Write:— | — | +1 | 07/23/2024 | ||||
| 131K | 0.3s | 104tps | $0.72/M | $0.72/M | — | | 07/23/2024 |