Meta: Llama v2 70B Chat (nitro)


Updated Mar 74,096 context
$0.9/M input tkns$0.9/M output tkns

The flagship, 70 billion parameter language model from Meta, fine tuned for chat completions. Llama 2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align to human preferences for helpfulness and safety.

Note: this is a higher-throughput version of this model, and may have higher prices and slightly different outputs.