Llama 3.3 70B Versatile
JSON →A versatile 70-billion-parameter instruction-tuned model from Meta capable of handling complex reasoning, coding, and multilingual tasks.
Specs
context window 128K tokens
max output 33K tokens
input price $0.59 / 1M tokens
output price $0.79 / 1M tokens
Capabilities
streamingcode-generationfunction-callingtool-usejson-modereasoning
Dates
releasedDec 2024
knowledge cutoffApr 2024
Resources
homepagellama.meta.com/ ↗
API
full doc /v1/models/llama-3.3-70b-versatile