Model Insights
The second largest chat model in Llama 2 family of LLMs developed and publicly released by Meta. This model was pretrained on 2 trillion tokens of data from publicly available sources and fine-tuned on over one million human-annotated instruction datasets.
Model
Details
Developer
Meta
License
Llama 2
Model parameters
13B
Pretraining tokens
2T
Release date
July 2023
Supported context length
4k
Price for prompt tokens*
$0.25/Million tokens
Price for response tokens*
$0.25/Million tokens
*Note: Data based on 11/14/2023
Here's how Llama-2-13b-chat performed across all three task types
Digging deeper, here’s a look how Llama-2-13b-chat performed across specific datasets
💰 Cost insights
The model offers a decent balance of cost and performance. It is 8x cheaper compared to GPT3.5 and 4x cheaper compared to Llama 70b variant.