Llama 4 Scout

MetaStandard

Open-weight 17B active params (109B total MoE). Strong multilingual and long-context performance.

Pricing

Input (per 1M tokens)
$0.18
Output (per 1M tokens)
$0.35

Cost Examples

ScenarioCost
100 chat messages (500 in / 200 out each)$0.0160
1K API calls (2K in / 500 out each)$0.5350
10K short requests (200 in / 100 out each)$0.7100
1M tokens input + 100K output$0.2150

Capabilities

Context Window
512K
Max Output
33K
Speed
100 tok/s
Released
2025-04-05
YesVision
YesTool Use
YesStreaming
YesJSON Mode

API Details

Model IDmeta-llama/Llama-4-Scout-17B-16E-Instruct
API Endpointhttps://api.together.xyz/v1/chat/completions
Last Updated2026-04-12

Other Meta Models

Llama 4 MaverickFlagship
$0.27 in / $0.85 out per 1M tokens
Llama 3.3 70BStandard
$0.20 in / $0.20 out per 1M tokens
Open Cost Calculatorto compare Llama 4 Scout costs with other models