# Stable Point Aware 3D

> Stable Point Aware 3D is a paid API for AI agents from Stability AI at stability-ai.mpp.paywithlocus.com, paid per call via MPP, $0.115/call, status unknown (last checked 2026-10-13).

Converts a 2D image of an object into a 3D model using Stability AI's point-aware reconstruction

## Facts

- Endpoint: POST https://stability-ai.mpp.paywithlocus.com/stability-ai/stable-point-aware-3d?utm_source=zero.xyz
- Price: $0.115/call
- Payment: MPP
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 3
- Provider: Stability AI
- Docs: https://platform.stability.ai/docs/api-reference
- Website: https://stability.ai
- Tags: image-generation, stable-diffusion, upscaling, 3d, ai, media
- Canonical page: https://www.zero.xyz/c/stability-ai-stable-point-aware-3d-d58f2b5b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_z87mPoH0XMlw-p0zqmMBS

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability stability-ai-stable-point-aware-3d-d58f2b5b -d '<json body>'
```

Example prompt: Take this product photo I have and generate a 3D model from it using Stability AI's point-aware 3D — use 2048 texture resolution, a guidance scale of 3, and a foreground ratio of 1.3.

## When to prefer this

Use this endpoint when you need to generate a 3D model from a single 2D image, especially for product visualization, game asset creation, or any workflow requiring a textured 3D mesh. Prefer this over manual modeling when speed matters and you have a clean photograph of the object. Choose this over generic 3D generation when your input is an existing image rather than a text prompt.

## Known failure modes

- Image does not contain a clearly isolated object — results in poor or deformed 3D geometry
- Unsupported texture resolution value other than 512/1024/2048 causes validation error
- Image format or encoding not accepted — returns 4xx error
- Object too complex or occluded for single-view reconstruction — low quality output
- Network timeout on large texture resolutions — batch latency may be high

## How this service works

Generate a 3D GLTF model with point-cloud awareness (SPAR3D).

## Output

A 3D model/mesh reconstructed from the input image, with texture detail corresponding to the requested texture resolution (512, 1024, or 2048). The output represents a point-aware 3D reconstruction of the object depicted in the source image.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "image"
 ],
 "properties": {
  "seed": {
   "type": "number",
   "description": "Random seed"
  },
  "image": {
   "type": "string",
   "description": "Source image of the object Send a public HTTPS URL (recommended; files up to 10 MiB) or base64/data URI. Hosted MPP JSON requests must stay below 8 KiB, so use a URL for larger files."
  },
  "guidance_scale": {
   "type": "number",
   "description": "Generation guidance scale (default 3)"
  },
  "foreground_ratio": {
   "type": "number",
   "description": "Subject scale in frame (default 1.3)"
  },
  "texture_resolution": {
   "type": "number",
   "description": "512|1024|2048 (default 1024)"
  }
 },
 "additionalProperties": true
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/stability-ai-stable-point-aware-3d-d58f2b5b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from stability-ai.mpp.paywithlocus.com](https://www.zero.xyz/host/stability-ai.mpp.paywithlocus.com/llms.txt)