[Gemini API] Add printable version for tutorials/documentation

Introduction: In today's digital age, harnessing AI is essential for innovation. Meet Gemini API, Google's powerful generative AI that offers free API calls for text and image processing. Whether you're a developer or just curious, this step-by-step guide will show you how to get started, from obtaining your API key to making your first request. Unlock the potential of generative AI for free and transform your projects effortlessly! Steps to Get Gemini API Key: Navigate to https://aistudio.google.com/app/apikey and Login with your Google Account. Fetching List of Gemini AI Models Available: To make the most out of the Gemini API, it’s essential to know the available AI models. This API call provides a list of all Gemini AI models, allowing you to select the most appropriate model for your specific use case. For example, for image processing, you might choose the "gemini-pro-vision" model. Use the following endpoint to get the list of available Gemini AI models: https://generativelanguage.googleapis.com/v1beta/models?key=<> Type - GET request. Simple Text Processing using the Gemini API: Utilizing the Gemini API for text processing offers a versatile range of models to cater to diverse needs. This section illustrates how to make a POST request to generate text using any model from the available list. Use the following endpoint to get the text response using the "gemini-pro" Gemini Model: https://generativelanguage.googleapis.com/v1/models/gemini-pro:generateContent?key=<> Type - POST request. Request Body (JSON) - { "contents":[ { "parts":[{"text": "Write a Short Poem"}]} ] } Response Body - { "candidates": [ { "content": { "parts": [ { "text": "**Tranquil Solitude**\n\nIn tranquility's embrace,\nWhere solitude weaves its lace,\nI find solace in nature's art,\nA sanctuary within my heart.\n\nThe gentle breeze whispers secrets,\nAs rustling leaves paint vibrant hues,\nBeneath the azure sky's canvas,\nA symphony of colors ensues.\n\nFar from worldly noise and strife,\nI seek solace in this serene life,\nWhere peace and contemplation reside,\nAnd harmony echoes with each stride." } ], "role": "model" }, "finishReason": "STOP", "index": 0, "safetyRatings": [ { "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "probability": "NEGLIGIBLE" }, { "category": "HARM_CATEGORY_HATE_SPEECH", "probability": "NEGLIGIBLE" }, { "category": "HARM_CATEGORY_HARASSMENT", "probability": "NEGLIGIBLE" }, { "category": "HARM_CATEGORY_DANGEROUS_CONTENT", "probability": "NEGLIGIBLE" } ] } ], "usageMetadata": { "promptTokenCount": 4, "candidatesTokenCount": 99, "totalTokenCount": 103 } } Simple Image Processing using the Gemini API: The Gemini API offers powerful image processing capabilities, allowing you to extract information and insights from images with ease. This section outlines how to make a POST request to obtain image extraction results using the "gemini-pro-vision" model. To perform image processing tasks, utilize the following endpoint with the "gemini-pro-vision" model: https://generativelanguage.googleapis.com/v1/models/gemini-pro-vision:generateContent?key=<> Type - POST request. Request Body (JSON) Text written between <<>> are for instructions. You need to replace it. { "contents":[ { "parts":[ {"text": "<>"}, { "inlineData": { "mimeType": "image/png", "data": "<>" } } ] } ] } Response Body - { "candidates": [ { "content": { "parts": [ { "text": " {"<>"}" } ], "role": "model" }, "finishReason": "STOP", "index": 0, "safetyRatings": [ { "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "probability": "NEGLIGIBLE" }, { "category": "HARM_CATEGORY_HATE_SPEECH", "probability": "NEGLIGIBLE" }, { "category": "HARM_CATEGORY_HARASSMENT", "probability": "NEGLIGIBLE" }, { "category": "HARM_CATEGORY_DANGEROUS_CONTENT", "probability": "NEGLIGIBLE" } ] } ], "usageMetadata": { "promptTokenCount": 267, "candidatesTokenCount": 267, "totalTokenCount": 534 } } Conclusion: In conclusion, the Gemini API offers a seamless solution for text and image processing tasks. With its user-friendly interface and powerful capabilities, developers can easily integrate AI-driven features into their applications. By leveraging the Gemini API, businesses can streamline workflows, enhance user experiences, and stay ahead in today's fast-paced digital landscape. Get started with the Gemini API today and unlock the potential of artificial intelligence to drive innovation and growth. Google Gemini offers a free tier, but it comes with limitations on how many requests you can make per minute (RPM). Here's a breakdown: Gemini 1.0 Pro (text and image only): This is the free tier version currently available for production use. It allows 15 requests per minute (RPM). Gemini 1.5 Flash (preview): This faster model is free to use in preview mode, but with a lower rate limit of 15 requests per minute (RPM). Gemini 1.5 Pro (preview): This high-performance model is also in preview and free to use, but it has the strictest rate limit of only 2 requests per minute (RPM). Google Gemini API Documentation: https://ai.google.dev/gemini-api/docs/api-overview