Models/Meta/Llama 4 Scout

Llama 4 Scout

Name: Llama 4 Scout API access
Brand: Meta

Meta · Open weights · Released Apr 5, 2025 · meta-llama/llama-4-scout

Compare Estimate cost

1.31M contextVisionToolsStructured outputPrompt cachingOpen weights

Available from 4 providersUSD / MTOK · VERIFIED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
DeepInfra	$0.10	$0.30	—	328K	fp8	0.41s	50 tok/s	99.9%
Groq	$0.11	$0.34	$0.055	131K	—	0.67s	439 tok/s	99.7%
Novita	$0.18	$0.59	—	131K	bf16	0.86s	77 tok/s	99.9%
Google	$0.25	$0.70	—	1.31M	—	0.72s	208 tok/s	99.9%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 44 hours ago

About

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

Specifications

Context window1,310,720

Max output16,384

Modalities intext, image

Modalities outtext

LicenseOpen weights

ReleasedApr 5, 2025

Knowledge cutoff2024-08-31

TokenizerLlama4

WeightsHugging Face ↗

Open weightsGATED

Hugging Facemeta-llama/Llama-4-Scout-17B-16E-Instruct ↗

Downloads342.1K

Likes1.3K

Licenseother

safetensorspytorch

Llama Guard 4 12B$0.18 / $0.18 Llama 4 Maverick$0.20 / $0.696 Llama 3.3 70B Instruct$0.10 / $0.32 Llama 3.2 1B Instruct$0.027 / $0.201

Compare: Llama 4 Scout vs Llama 4 Maverick

Embed badge

[![Llama 4 Scout](https://modelindex.ai/badge/meta-llama/llama-4-scout)](https://modelindex.ai/models/meta-llama/llama-4-scout)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

Hugging Face4 minutes ago

COMMUNITY

ModelIndex benchmarks44 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.