Llama 4 Maverick 17B 128E Instruct
JSON →A 17-billion-parameter mixture-of-experts instruction-tuned model from Meta with 128 experts, optimized for high-performance reasoning and coding.
Specs
context window 131K tokens
max output 8K tokens
input price $0.2 / 1M tokens
output price $0.6 / 1M tokens
Capabilities
streamingcode-generationfunction-callingtool-usejson-modereasoningvision
Dates
releasedApr 2025
knowledge cutoffDec 2024
Resources
homepagellama.meta.com/ ↗