Pixal3D API
$0.25/gen
Developer-ready API access
Turn the early momentum around Tencent Pixal3D into a developer-ready image-to-3D workflow. PiAPI is preparing Pixal3D API access for teams that want 3D generation inside apps, tools, and production pipelines.
Pay-as-you-go access through PiAPI.
$0.25/gen
Developer-ready API access
Based on public model and research references — final API details will be confirmed at launch.
Pixal3D is an image-to-3D model associated with TencentARC and Tsinghua University research, designed around pixel-aligned generation that preserves visible image details more faithfully in the resulting 3D asset.
Start from a single reference image — object photo, product shot, concept art, or asset sketch — and prepare a repeatable path toward generated 3D assets in GLB-style formats.
Plan around PiAPI's familiar pattern: submit an image, create an async task, poll task status, and retrieve the generated asset URL — instead of a manual browser-only demo flow.
Game asset prototyping, ecommerce 3D product previews, AR/VR content workflows, creative tool integrations, and automated batch 3D asset pipelines.
Track Pixal3D alongside PiAPI's broader 3D model options as availability opens — one account, one task workflow, no separate queue layer to build.
Trellis is the practical choice for teams that need 3D API access today. Pixal3D is the model to watch if your roadmap depends on TencentARC's pixel-aligned image-to-3D research.
Sign up and grab an API key from the PiAPI workspace — free credits are included on sign-up.
Add credits on the billing page when you are ready to scale beyond the free tier.
POST your first task following the API docs, then poll the task until the result is ready.
Prototype prompts and settings in the the playground above before wiring them into your product.
curl -X POST 'https://api.piapi.ai/api/v1/task' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "Qubico/pixal3d",
"task_type": "image-to-3d",
"input": {
"image": "YOUR_IMAGE_URL",
"seed": 0
}
}'
# → { "task_id": "9d5a…", "status": "pending" }curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'
# poll until status = completed
{
"data": {
"status": "completed",
"output": {
"model_file": "https://img.theapi.app/ephemeral/…"
}
}
}$ npm install -g piapi-cli $ piapi run pixal3d-api \ image=YOUR_IMAGE_URL \ seed=0 ✓ Task completed! https://img.theapi.app/ephemeral/…
Pixal3D is an image-to-3D AI model associated with TencentARC and Tsinghua University research. It focuses on pixel-aligned 3D generation from input images.
Pixal3D API access is emerging through third-party providers. PiAPI is preparing Pixal3D API access for developers who want a unified image-to-3D workflow.
Pixal3D API support is planned and coming soon on PiAPI. Join the waitlist or contact the team to get updates as integration details are finalized.
Developers can use Pixal3D-style image-to-3D generation for game asset prototyping, ecommerce 3D previews, AR and VR content, creative tools, and automated 3D asset pipelines.
Public model and paper references associate Pixal3D with TencentARC and Tsinghua University researchers. PiAPI is not an official Tencent page or Tencent affiliate.
Current Pixal3D demos and API pages commonly reference GLB-style 3D model outputs. Final PiAPI output formats will be confirmed when Pixal3D support launches.
Pixal3D is best described as an emerging TencentARC image-to-3D model focused on pixel-aligned generation from images, while Trellis is an established 3D generation API option already available on PiAPI. Developers can use Trellis today and track Pixal3D for upcoming image-to-3D API availability.
More questions? See the API docs.