Skip to main content

Overview

Make.com (formerly Integromat) is a powerful no-code automation platform. Using its built-in HTTP request node (Make a request), you can directly call APIYI’s Gemini native format API for image understanding, content analysis, and other multimodal automation workflows — no coding required.
Integration Info
  • 🔧 Tool: Make.com (make.com)
  • 🔌 Integration: HTTP request node (Make a request)
  • 🤖 Model: Gemini series (via APIYI Gemini native format)
  • 📡 API Endpoint: https://api.apiyi.com/v1beta/models/{model}:generateContent

Why Make.com + APIYI

Zero-Code Integration

Configure HTTP request nodes through visual drag-and-drop, no coding needed to call AI models

Automated Workflows

Combine with Make.com triggers and conditional logic to build complete image processing automation

Multi-Model Support

APIYI supports 200+ models — one API key to switch between different AI capabilities in Make.com

Flexible Extension

Seamlessly connect with 1000+ apps including Google Sheets, Slack, Email, and more

Supported APIYI Models

Model NameModel IDUse CaseAPI Docs
Gemini 3.1 Pro Previewgemini-3.1-pro-previewImage understanding, text generationView Docs
Gemini 3 Pro Previewgemini-3-pro-previewImage understanding, image generationView Docs
Gemini 3 Flash Previewgemini-3-flash-previewImage understanding (fast)View Docs
Recommended: gemini-3.1-pro-preview for the strongest image understanding capabilities. For higher speed, choose the Flash series.

Setup Steps

1

Step 1: Get Your APIYI API Key

  1. Visit APIYI Console to register/login
  2. Go to the Tokens section and generate a new API key
  3. Copy the key (starts with sk-), you’ll need it for configuration
2

Step 2: Create a Make.com Scenario

  1. Log in to Make.com and click Create a new scenario
  2. Click + to add a module
  3. Search for and select the HTTP module
  4. Under Actions, select Make a request
3

Step 3: Configure the HTTP Request Node

Fill in the following configuration in the HTTP request node:URL:
https://api.apiyi.com/v1beta/models/gemini-3.1-pro-preview:generateContent
Method: POSTHeaders:
Header NameValue
Content-Typeapplication/json
AuthorizationBearer sk-your-APIYI-key
Body type: RawContent type: JSON (application/json)Request content (Body):
{
  "contents": [
    {
      "parts": [
        {
          "text": "What is in this image?"
        },
        {
          "fileData": {
            "mimeType": "image/png",
            "fileUri": "https://your-image-url-here"
          }
        }
      ]
    }
  ]
}
4

Step 4: Test Run

Click Run once to test the request and verify it returns correct image understanding results.

Complete Request Example

Here’s a complete image understanding request example that analyzes an otter image:
{
  "contents": [
    {
      "parts": [
        {
          "text": "What is in this image?"
        },
        {
          "fileData": {
            "mimeType": "image/png",
            "fileUri": "https://raw.githubusercontent.com/apiyi-api/ai-api-code-samples/refs/heads/main/Vision-API-OpenAI/otter.png"
          }
        }
      ]
    }
  ]
}

Request Parameters

FieldTypeRequiredDescription
contentsarrayYesConversation content array
contents[].partsarrayYesMessage parts (text + image)
parts[].textstringYesUser’s text prompt
parts[].fileData.mimeTypestringYesImage format: image/png, image/jpeg, image/webp, etc.
parts[].fileData.fileUristringYesPublicly accessible image URL
fileUri must be a publicly accessible image URL. If the image requires authentication, upload it to a public storage service first.

Practical Scenarios

Scenario 1: Auto-Analyze Email Attachment Images

  1. Trigger: Gmail - Watch emails (monitor new emails)
  2. Process: HTTP node calls Gemini image understanding
  3. Output: Write analysis results to Google Sheets or send to Slack

Scenario 2: E-commerce Product Image Auto-Tagging

  1. Trigger: Google Drive - Watch files (monitor newly uploaded images)
  2. Process: HTTP node analyzes product image content
  3. Output: Automatically add category tags to product images

Scenario 3: Social Media Content Moderation

  1. Trigger: Periodically fetch user-submitted images
  2. Process: HTTP node analyzes image content for compliance
  3. Output: Auto-flag non-compliant content for review

Advanced Tips

Dynamic Image URL Replacement

In Make.com, you can use output variables from upstream modules to dynamically replace fileUri for batch image analysis:
{
  "contents": [
    {
      "parts": [
        {
          "text": "Please describe this image and extract any text in it"
        },
        {
          "fileData": {
            "mimeType": "image/png",
            "fileUri": "{{upstream module's image URL variable}}"
          }
        }
      ]
    }
  ]
}

Switching Models

Simply change the model name in the URL to switch models:
NeedURL
Strongest understandinghttps://api.apiyi.com/v1beta/models/gemini-3.1-pro-preview:generateContent
High-speed analysishttps://api.apiyi.com/v1beta/models/gemini-3-flash-preview:generateContent

FAQ

Please check:
  1. Authorization Header format: Bearer sk-your-key (note the space after Bearer)
  2. API key is valid (verify in APIYI Console)
  3. Account balance is sufficient
Please verify:
  1. fileUri is a publicly accessible URL (can be opened directly in browser)
  2. mimeType matches the actual image format
  3. Image size is within model limits
The Gemini API returns JSON format. You can:
  1. Use Make.com’s JSON module to parse the response
  2. Extract the candidates[0].content.parts[0].text field for the analysis result
  3. Pass the result to downstream modules (e.g., write to database, send notifications)
Visit APIYI Console, register an account and generate a new key in the Tokens section. New users get free test credits.
Yes. Replace fileData with inlineData:
{
  "inlineData": {
    "mimeType": "image/png",
    "data": "Base64-encoded-image-data"
  }
}