Ultimate AI media · API platform
Peak Pixels, Boundless Inspiration
Bringing together a curated selection of the world's top trending AI models, the next-generation PureApi completely redefines image quality and rendering speed. Break through technical barriers, unleash true productivity, and scale your creative output without limits.
Featured models
Curated entry points — browse the full catalog, credits, and queue paths in the console.
seedance-2.0-text-to-video
Seedance 2.0 Text to Video
seedance-2.0-video-extend
Seedance 2.0 Video Extend
wan-2.6-image-edit
Wan 2.6 Image Edit
wan-2.7-text-to-video
Wan 2.7 Text To Video
wan-2.7-video-edit
Wan 2.7 Video Edit
wan-2.7-image-to-video
Wan 2.7 Image To Video
Built for developers
Integrate with a single HTTP contract
Queue a job, poll status, and settle billing — same JSON shape across launch models. Use cURL in CI or wrap the endpoint in your backend SDK.
- API keysCreate, rotate, and revoke keys from the console.
- ExamplescURL, Python, and Node snippets ship next to each model.
- UsageRequest logs for status, latency, and credit movement.
curl -X POST "$BASE_URL/api/gateway/queue/seedance-2.0-text-to-video" \
-H "Authorization: Key $API_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt":"A cinematic product reveal, soft lighting, smooth camera motion","duration":"auto","resolution":"720p","aspect_ratio":"auto","generate_audio":false}'Engineered for velocity
Ship integrations quickly, then keep operating costs and failure modes under control.
Broad model access
Route image, video, and edit jobs through one gateway with a stable response contract.
Fast async queues
Submit, poll status, and stream results without blocking your application servers.
Built to scale
From first integration to sustained traffic — usage logs, errors, and limits stay predictable.
Security-minded
API keys, server-side pricing, and frozen credits reduce surprise bills and client tampering.
Stripe recharge & settlement
Top up account credits through Stripe Checkout. Public API pricing is resolved server-side from the model registry — clients never dictate cost.
One response shape
Parse once in your worker layer — extend to new models without redesigning your state machine.
{
"request_id": "uuid",
"model": "seedance-2.0-text-to-video",
"status": "IN_PROGRESS",
"billing": {
"cost_credits": 0,
"charge_status": "FROZEN"
}
}