Gemini API & Google AI · Lesson 2
Gemini Model Lineup and Choosing for the Task
Gemini 2.0 Flash vs 1.5 Pro vs 1.5 Flash vs Ultra: context, price, speed, and how to pick a model for the task and budget.
Practical exercise
What to do after this lesson
Write a script that uses genai.list_models() to print all models supporting generateContent with their input/output limits, and for three scenarios (cheap chat, analyzing a 200-page PDF, bulk-classifying 100k records) prints the recommended model with rationale.
Task grader
Write a script that uses genai.list_models() to print all models supporting generateContent with their input/output limits, and for three scenarios (cheap chat, analyzing a 200-page PDF, bulk-classifying 100k records) prints the recommended model with rationale.
Ready-to-use prompt
Template for this lesson
Copy and adapt to your context. Text in angle brackets should be replaced.
Help me choose a Gemini model. Task: <description> Average input size: <tokens> Request volume: <per day/month> Budget: <if any> Compare gemini-2.0-flash / 1.5-pro / 1.5-flash / 1.5-flash-8b by context, input/output price, speed. Give a recommendation with rationale and cost estimate.