{"type":"video","version":"1.0","html":"<iframe src=\"https://www.loom.com/embed/e083074597fa4722bde3fe045381d0e1\" frameborder=\"0\" width=\"1728\" height=\"1296\" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>","height":1296,"width":1728,"provider_name":"Loom","provider_url":"https://www.loom.com","thumbnail_height":1296,"thumbnail_width":1728,"thumbnail_url":"https://cdn.loom.com/sessions/thumbnails/e083074597fa4722bde3fe045381d0e1-700b5e4832978e77.gif","duration":419.509,"title":"Evaluating Gemini API Performance 🚀","description":"Hi, in this video, I showcase an evaluation example using the Gemini API to understand how temperature impacts the number of generated tokens and response time. I demonstrate building request bodies, processing responses, and visualizing data in Postman. No action requested, just insights on API performance."}