🧠 AI ProvidersGoogle Gemini

Google Gemini

Integrate Gemini 2.0 Flash, Gemini Pro, and Imagen with ProtectMyAPI.

🔬

Supported Models: Gemini 2.0 Flash, Gemini 1.5 Pro, Gemini 1.5 Flash, Imagen 3

Features

  • ✅ Text generation
  • ✅ Vision (image analysis)
  • ✅ Audio understanding
  • ✅ Video understanding
  • ✅ Image generation (Imagen)
  • ✅ Search Grounding
  • ✅ Function Calling
  • ✅ Streaming responses

Setup

1. Add your API key to Secrets

In the ProtectMyAPI dashboard:

  1. Go to your app → Secrets
  2. Add a secret named GOOGLE_AI_API_KEY
  3. Paste your Google AI API key as the value

2. Create an endpoint

Create an endpoint with:

  • Name: Gemini Generate
  • Slug: gemini-generate
  • Target URL: https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key={{GOOGLE_AI_API_KEY}}
  • Method: POST

Code Examples

import ProtectMyAPI
 
// Simple text generation
let response = try await ProtectMyAPI.shared.request(
    endpoint: "gemini-generate",
    method: .POST,
    body: [
        "contents": [
            [
                "parts": [
                    ["text": "Explain how AI works"]
                ]
            ]
        ]
    ]
)
 
// With system instruction
let response = try await ProtectMyAPI.shared.request(
    endpoint: "gemini-generate",
    method: .POST,
    body: [
        "system_instruction": [
            "parts": [["text": "You are a helpful coding assistant."]]
        ],
        "contents": [
            [
                "parts": [
                    ["text": "Write a Python function to reverse a string"]
                ]
            ]
        ]
    ]
)
 
// Vision (image analysis)
let imageData = UIImage(named: "photo")!.jpegData(compressionQuality: 0.8)!
let base64Image = imageData.base64EncodedString()
 
let visionResponse = try await ProtectMyAPI.shared.request(
    endpoint: "gemini-generate",
    method: .POST,
    body: [
        "contents": [
            [
                "parts": [
                    ["text": "What's in this image?"],
                    [
                        "inline_data": [
                            "mime_type": "image/jpeg",
                            "data": base64Image
                        ]
                    ]
                ]
            ]
        ]
    ]
)

Models

ModelBest ForContext
gemini-2.0-flashFast, multimodal1M
gemini-1.5-proComplex tasks2M
gemini-1.5-flashFast responses1M

Search Grounding

Ground responses with Google Search:

let response = try await ProtectMyAPI.shared.request(
    endpoint: "gemini-generate",
    method: .POST,
    body: [
        "contents": [
            [
                "parts": [["text": "What are the latest AI news?"]]
            ]
        ],
        "tools": [
            ["google_search": [:]]
        ]
    ]
)

Audio Understanding

let audioData = // your audio as base64
let response = try await ProtectMyAPI.shared.request(
    endpoint: "gemini-generate",
    method: .POST,
    body: [
        "contents": [
            [
                "parts": [
                    ["text": "Transcribe this audio"],
                    [
                        "inline_data": [
                            "mime_type": "audio/mp3",
                            "data": audioData
                        ]
                    ]
                ]
            ]
        ]
    ]
)

Image Generation (Imagen)

Create an endpoint for Imagen:

  • Slug: imagen-generate
  • Target URL: https://generativelanguage.googleapis.com/v1beta/models/imagen-3.0-generate-001:predict?key={{GOOGLE_AI_API_KEY}}
let imageResponse = try await ProtectMyAPI.shared.request(
    endpoint: "imagen-generate",
    method: .POST,
    body: [
        "instances": [
            ["prompt": "A futuristic city at sunset"]
        ],
        "parameters": [
            "sampleCount": 1
        ]
    ]
)
AnthropicMistral AI