Llama 4 Maverick
META-LLAMA Developer Architecture Profile
Intelligence (ELO)1423Chatbot Arena Verified
Max Context Limit1,048,576Max Out: 16,384 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$0.84Blended Standard Rate
Model Capabilities & Contract SLAs
- Coding & Logic
- Fictional
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 forward...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$0.19 / 1M
Output Tokens (Completion)$0.65 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupLlama 4 Maverick vs Qwen: Qwen3.5 Plus 2026-04-20VS Engine MatchupLlama 4 Maverick vs Qwen: Qwen3.5 Plus 2026-02-15VS Engine MatchupLlama 4 Maverick vs Anthropic: Claude Haiku 4.5 (batch)VS Engine MatchupLlama 4 Maverick vs Relace: Relace Apply 3VS Engine MatchupLlama 4 Maverick vs Qwen: Qwen3 Next 80B A3B ThinkingVS Engine MatchupLlama 4 Maverick vs Mistral: Mistral Medium 3