TokenCosts AI.iov1.0
Back to Models Directory
Metallama-4-scout2026 Frontier

Meta: Llama 4 Scout API Pricing

Official PricingCall via OpenRouter

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...

Base Input Price$0.10/ 1M tokens
Base Output Price$0.30/ 1M tokens
Prompt Cache Read$0.100-0% discount
Batch API RateN/A24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
Meta Direct$0.10$0.30Not availableConnect
OpenRouter$0.10$0.30Not availableConnect

Head-to-Head Comparisons for Meta: Llama 4 Scout

Meta: Llama 4 Scout vs OpenAI: GPT-6.1 Sol$0.1/M vs $2/M
Meta: Llama 4 Scout vs GPT-4o (Omni)$0.1/M vs $2.5/M
Meta: Llama 4 Scout vs Claude 3.5 Sonnet$0.1/M vs $3/M
Meta: Llama 4 Scout vs DeepSeek-V3 (deepseek-chat)$0.1/M vs $0.27/M