← Back to Directory

Llama 4 Scout

META-LLAMA Developer Architecture Profile

OpenRouter ↗HuggingFace ↗
Intelligence (ELO)1059Chatbot Arena Verified
Max Context Limit1,310,720Max Out: 16,384 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$0.40Blended Standard Rate

Model Capabilities & Contract SLAs

    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...

    Granular Pricing Matrix

    Input Tokens (Standard Prompt)$0.10 / 1M
    Output Tokens (Completion)$0.30 / 1M

    Pricing data via OpenRouter. Sync: 10/2/2026

    Evaluate Competitors

    VS Engine MatchupLlama 4 Scout vs IBM: Granite 4.0 MicroVS Engine MatchupLlama 4 Scout vs Qwen: Qwen3.8 27B (free)VS Engine MatchupLlama 4 Scout vs Free Models RouterVS Engine MatchupLlama 4 Scout vs Inception: Mercury 2.5VS Engine MatchupLlama 4 Scout vs Pareto Code RouterVS Engine MatchupLlama 4 Scout vs Poolside: Laguna S 2.1