Enterprise Video & Image API99.5% SLA, Zero Retry Logic
Multi-model failover, batch processing, webhook delivery, and enterprise-grade reliability. We handle the infrastructure so you don't wake up at 2am.
We Handle Failures. You Sleep.
When a provider goes down (and they do), your requests automatically route to the next available model. No retry logic in your code. No 2am pager alerts. The response tells you exactly what happened.
model_actual and failover_used in every response{
"id": "img_abc123",
"model_requested": "dall-e-3",
"model_actual": "gpt-image-1",
"failover_used": true,
"failover_reason": "dall-e-3: rate limited (429)",
"data": [
{ "url": "https://cdn.creativeai.run/images/abc123.png" }
]
}20 Videos in One Request
Submit up to 20 video generation jobs in a single API call. Each job fires its own webhook when complete. No polling loops needed.
curl -X POST https://api.creativeai.run/v1/video/generations/batch \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompts": [
{"prompt": "Product hero shot, 360 rotation", "image_url": "https://cdn.example.com/p1.png"},
{"prompt": "Social clip, dynamic transitions"},
{"prompt": "Drone shot over coastline at sunset"}
],
"model": "auto",
"duration": 5,
"webhook_url": "https://your-app.com/webhooks/video-batch"
}'{
"batch_id": "video_batch_xyz789",
"event": "video.completed",
"data": {
"job_id": "vid_abc123",
"status": "completed",
"output_url": "https://cdn.creativeai.run/videos/abc123.mp4",
"duration_seconds": 5,
"model_used": "kling-v3",
"thumbnail_url": "https://cdn.creativeai.run/thumbnails/abc123.jpg"
},
"timestamp": "2026-04-01T19:00:00Z",
"signature": "sha256=abc123..."
}HMAC-Signed, 3x Retry, 24h Retention
Every webhook includes an HMAC-SHA256 signature for verification. If your endpoint returns non-2xx, we retry 3 times with exponential backoff (0s, 5s, 30s). Results stay available in the status API for 24 hours.
Approved customer-facing line:
“Webhook delivery uses 3 attempts with exponential backoff (0s, 5s, 30s). If delivery still fails, the final result remains available via the status API.”
Enterprise Features
Everything you need for production AI generation workloads.
Multi-Model Failover
Automatic routing across Kling, Seedance, Vidu, Veo. If one provider fails, requests continue without interruption.
Batch Processing
Submit 1-20 videos per request. Perfect for product catalogs, marketing campaigns, and A/B testing at scale.
Async Webhooks
HMAC-signed callbacks when each job completes. 3 delivery attempts with exponential backoff. Status API fallback.
99.5% SLA
Written uptime guarantee for enterprise pilots. Service credits for downtime. Real-time status page.
Dedicated Support
Named account manager. Priority response SLA. Direct Slack channel for enterprise accounts.
Volume Pricing
Predictable per-generation pricing. Volume discounts for 10K+ generations/month. No surprises.
Simple Enterprise Pricing
Same per-generation pricing as self-serve. Volume discounts available.
Ready for Enterprise?
Get a dedicated pilot with custom capacity, SLA, and support.
Request Enterprise Pilot