TokenCosts AI.iov1.0
Back to Models Directory
Metallama-4-maverick2026 Frontier

Meta: Llama 4 Maverick API Pricing

Official PricingCall via OpenRouter

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per f...

Base Input Price$0.35/ 1M tokens
Base Output Price$1.00/ 1M tokens
Prompt Cache Read$0.170-51.43% 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$0.35$1.00SupportedConnect
OpenRouter$0.35$1.00SupportedConnect

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

Meta: Llama 4 Maverick vs OpenAI: GPT-6.1 Sol$0.35/M vs $2/M
Meta: Llama 4 Maverick vs GPT-4o (Omni)$0.35/M vs $2.5/M
Meta: Llama 4 Maverick vs Claude 3.5 Sonnet$0.35/M vs $3/M
Meta: Llama 4 Maverick vs DeepSeek-V3 (deepseek-chat)$0.35/M vs $0.27/M