Quickstart Guide
Get up and running with the Hydrilla AI API in 3 simple steps: authenticate, submit a 3D reconstruction task, and poll for the downloadable GLB mesh.
Before you start
You need an API key that starts with hyd_live_. Create one in the Authentication guide if you don't have one yet.
Create your API key
API requests require a key that starts with hyd_live_.
- Log in to the Hydrilla Studio.
- Open API Keys in your dashboard sidebar.
- Click Create Secret Key, give it a name (for example, Production-Backend), and copy the revealed API key.
Trigger 3D reconstruction
Submit a prompt to the POST /v1/3d/text-to-3d endpoint. Hydrilla compiles the prompt, renders concept views, and dispatches the job to the BlueFox GPU cluster.
curl -X POST https://backend.hydrilla.ai/v1/3d/text-to-3d \
-H "Authorization: Bearer hyd_live_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Futuristic cyberpunk vehicle, high details, game ready prop",
"image_model": {
"provider": "openai",
"quality": "high"
},
"resolution": 1536
}'The endpoint returns an asynchronous task ID:
{
"id": "job_c18ab44d03e192a40",
"status": "queued",
"resolution": 1536,
"links": {
"poll": "https://backend.hydrilla.ai/v1/3d/tasks/job_c18ab44d03e192a40"
}
}Poll for completion and download the mesh
Poll GET /v1/3d/tasks/:taskId every 2–3 seconds until the status reaches SUCCEEDED. Generation usually takes a few minutes.
curl -X GET https://backend.hydrilla.ai/v1/3d/tasks/job_c18ab44d03e192a40 \
-H "Authorization: Bearer hyd_live_your_api_key_here"{
"id": "job_c18ab44d03e192a40",
"status": "SUCCEEDED",
"progress": 100,
"result": {
"mesh_url": "https://storage.googleapis.com/hydrilla-meshes/job_c18ab.glb",
"preview_image_url": "https://storage.googleapis.com/hydrilla-meshes/job_c18ab_thumb.png",
"format": "glb",
"triangles": 128450
}
}Complete Python example
Run this self-contained script to test end-to-end 3D generation:
Next steps
Authentication
Key lifecycle, the Bearer header, and error codes.
Text to 3D
Full parameter reference for prompt-to-mesh generation.
Models & Engines
Compare models, speeds, and credit costs.