Make & Zapier + CreativeAI: AI Image & Video in Your Workflows
Add AI image and video generation to any Make or Zapier workflow using standard HTTP modules. CreativeAI's API is fully OpenAI-compatible — no custom app or partner integration needed. Just point an HTTP request at our endpoint and go.
How It Works (No Custom App Required)
CreativeAI uses a standard REST API with the same format as OpenAI. Both Make and Zapier support generic HTTP requests, so you connect directly — no marketplace app, no OAuth dance, no waiting for a connector to be approved.
Why CreativeAI for Make & Zapier?
Multi-Model Failover
If one provider goes down, your scenario keeps running. Automatic failover across GPT Image, Flux, Seedream, and more.
Standard HTTP — No Custom App
Use Make's HTTP module or Zapier's Webhooks action. No marketplace app needed — works today, right now.
Images + Video from One API
Generate images AND videos without juggling multiple API providers in your scenario.
Webhook Delivery
For async video jobs, receive results via webhook — no polling loop needed. HMAC-signed payloads with automatic retries.
Prerequisites
Image Generation
In Make, add an HTTP > Make a request module to your scenario:
| Module | HTTP > Make a request |
| URL | https://api.creativeai.run/v1/images/generations |
| Method | POST |
| Headers | Authorization: Bearer YOUR_API_KEYContent-Type: application/json |
| Body type | Raw > JSON |
Make tip: Check "Parse response" so subsequent modules can map data[].url directly as a variable.
Request Body (same for both platforms)
{
"model": "dall-e-3",
"prompt": "Professional product photo of wireless headphones on marble surface, soft lighting",
"size": "1024x1024",
"n": 1
}Response
{
"created": 1709827200,
"data": [
{
"url": "https://cdn.creativeai.run/images/abc123.png",
"revised_prompt": "Professional product photo of wireless headphones..."
}
],
"model_actual": "gpt-image-1",
"failover_used": false
}Video Generation (Async)
Video generation is asynchronous — you submit a request, receive a task_id, then either poll for the result or receive it via webhook. Both approaches work in Make and Zapier.
Option A: Poll with Sleep Module
Option B: Webhook (Recommended)
Set up a Webhooks > Custom webhook trigger in a separate Make scenario. Pass that webhook URL in your video generation request as webhook_url. CreativeAI will POST the completed result to your webhook — no polling needed.
Video Request Body
{
"model": "kling-v2-master",
"prompt": "Drone aerial shot of coastal cliffs at golden hour, cinematic",
"duration": "5",
"aspect_ratio": "16:9"
}Completed Response (poll or webhook payload)
{
"task_id": "vid_abc123",
"status": "completed",
"video_url": "https://cdn.creativeai.run/videos/abc123.mp4",
"duration": 5,
"resolution": "1080p"
}Timing: Video generation takes 30-120 seconds. If using the polling approach, a 60-second delay covers most cases. For production workflows, the webhook approach is more reliable and doesn't consume extra task runs.
Webhook-Driven Workflows
For async jobs (especially video), webhooks are the cleanest pattern. CreativeAI sends an HMAC-signed POST to your webhook URL when a generation completes.
Webhook Payload
// CreativeAI webhook payload (POST to your Make/Zapier webhook URL)
{
"event": "generation.completed",
"task_id": "vid_abc123",
"status": "completed",
"result": {
"url": "https://cdn.creativeai.run/videos/abc123.mp4",
"duration": 5,
"resolution": "1080p"
},
"metadata": {
"model": "kling-v2-master",
"created_at": "2026-03-10T14:30:00Z"
}
}Make Setup
- Create a new scenario with Webhooks > Custom webhook trigger
- Copy the webhook URL Make generates
- Pass it as
webhook_urlin your video generation request - Add downstream modules (Slack, Drive, email, etc.)
Zapier Setup
- Create a new Zap with Webhooks by Zapier > Catch Hook trigger
- Copy the catch hook URL Zapier generates
- Pass it as
webhook_urlin your video generation request - Add downstream actions (Slack, Google Sheets, email, etc.)
Security: All webhooks are signed with HMAC-SHA256 via the X-CreativeAI-Signature header. See our webhooks documentation for verification code.
Example Workflows
E-Commerce: Auto-Generate Product Visuals
Social Media: Schedule + Generate Graphics
Video Pipeline: Generate + Store + Notify
Zapier Code Step Example
// Zapier "Code by Zapier" (JavaScript) — build image request
const prompt = inputData.caption || "A beautiful landscape";
const style = inputData.style || "photorealistic, professional";
output = {
request_body: JSON.stringify({
model: "dall-e-3",
prompt: prompt + ". Style: " + style,
size: "1024x1024",
n: 1
})
};Available Models
Image Models
- Popular
dall-e-3— GPT Image (OpenAI) - Best
flux-pro— Flux Pro (Black Forest) - Budget
seedream-3.0— Seedream (ByteDance) - Premium
ideogram-v3— Ideogram V3
Video Models
- Popular
kling-v3— Kling V3 Pro - Best
kling-o3-pro— Kling O3 Pro - Fast
seedance-1.5— Seedance 1.5 (ByteDance)
Rate Limits & Concurrency
| Tier | Image/min | Video/min | Concurrent |
|---|---|---|---|
| Free | 10 | 3 | 5 |
| Pay-as-you-go | 30 | 10 | 15 |
| Enterprise | Custom | Custom | Custom |
Frequently Asked Questions
Is there an official CreativeAI app on Make or Zapier?
Not yet. Our API is fully OpenAI-compatible, so you use the built-in HTTP module (Make) or Webhooks by Zapier action — no custom app needed. This actually gives you more flexibility than a marketplace app since you have full control over headers, payloads, and error handling.
How do I handle errors in my scenario?
CreativeAI returns standard HTTP status codes (400, 401, 429, 500) with JSON error bodies. In Make, use the built-in error handler on the HTTP module to retry or route to an alert. In Zapier, failed steps auto-retry on 5xx errors. For 429 rate limits, add a short delay before retry.
Can I use Make/Zapier with CreativeAI's webhook delivery?
Yes — this is the recommended approach for video workflows. Use a Custom webhook trigger (Make) or Catch Hook trigger (Zapier) and pass the generated URL as webhook_url in your video generation request. See our webhooks docs for full details.
Does this count as extra task runs / operations?
Each HTTP request to CreativeAI counts as one Make operation or one Zapier task run. For video with polling, the submit + poll = 2 operations. Using the webhook approach keeps it to 1 operation per scenario (the webhook trigger is free in both platforms).
Migrating from another provider?
If your Make or Zapier workflow calls OpenAI's DALL-E, Gemini, or Sora APIs directly via HTTP, switching to CreativeAI is a one-line change — update the base URL to https://api.creativeai.run and swap in your CreativeAI API key. The request/response format is identical.