Image to 3D mesh
$0.24
- Mesh-only GLB output
Meshy 3D API / for image-to-3D and text-to-3D generation
Use through PiAPI to submit asynchronous 3D generation tasks and retrieve a completed GLB asset.
Pay per successful generation through PiAPI.
$0.24
from $0.36
from $0.24
Send an image URL and choose mesh-only output or textured output at 2K, 4K, or 8K texture resolution.
Start a text-to-3D preview task with a prompt, then use its completed PiAPI task_id for refinement.
The refine request accepts preview_task_id and returns a completed GLB model through the same task polling flow.
Submit a task to PiAPI, poll its task status or use a webhook, and read the finished model from output.model_file.
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": "meshy",
"task_type": "image-to-3d",
"input": {
"image_url": "YOUR_IMAGE_URL",
"should_texture": true,
"texture_resolution": "2k"
}
}'curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'model_file
curl -X POST 'https://api.piapi.ai/api/v1/task' \
-H 'X-API-Key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{
"model": "meshy",
"task_type": "text-to-3d",
"input": {
"mode": "preview",
"prompt": "A ceramic teapot",
"texture_resolution": "2k"
}
}'curl 'https://api.piapi.ai/api/v1/task/{task_id}' \
-H 'X-API-Key: YOUR_API_KEY'model_file
Create a preview with mode=preview, wait for it to complete, then send its PiAPI task_id as preview_task_id with mode=refine.
The estimate changes with should_texture and texture_resolution. The Workspace displays the selected estimate before submission.
See the Meshy create-task and get-task API documentation linked from this page.
More questions? See the API docs.