{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/bd4e9029a1da4fd4a3e40e41c87ebb3a\" frameborder=\"0\" width=\"1114\" height=\"835\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":835,"width":1114,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":835,"thumbnail_width":1114,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/bd4e9029a1da4fd4a3e40e41c87ebb3a-1696395774096.gif","duration":124.20057128000002,"title":"LiteLLM - Call 100+ LLMs in one Input/Output Format","description":"Hey, in this video, I'll be demonstrating how to use light.lm, a tool that allows you to make API calls and chat completions using the OpenAI chat completion format. With light.lm, you can easily call over 100 different language models, including GPT 3.5 and Hugging Face models, all in the same input and output format. I'll show you an example of how to use light.lm and explain how you can make completion calls to different models, track costs, and even cache responses. So, let's get started!"}