# Hunyuan 3D V2.1

Hunyuan3D-2.1 is a scalable 3D asset generation system that enhances state-of-the-art 3D creation with Physically-Based Rendering (PBR).

## API Information

- **Model Slug:** hunyuan-3d-v2-1
- **Branded URL:** https://www.eachlabs.ai/tencent/hunyuan-3d/hunyuan-3d-v2-1
- **Provider:** Tencent
- **Category:** Image to 3D
- **Output Type:** object
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Fixed pricing: $0.3 per request
- **Estimated Processing Time:** 290 seconds
- **Last Updated:** 2026-06-08
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/hunyuan-3d-v2-1

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.3000
- **Pricing Details:** Fixed pricing: $0.3 per request

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Fixed pricing: $0.3 per request |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| input_image_url | string | Yes | - | - | URL of image to use while generating the 3D model. |
| seed | integer | No | - | - | The same seed and the same prompt given to the same version of the model will output the same image every time. |
| num_inference_steps | integer | No | 50 | 1–50 | Number of inference steps to perform. |
| guidance_scale | number | No | 7.5 | 0–20 | Guidance scale for the model. |
| octree_resolution | integer | No | 256 | 1–1024 | Octree resolution for the model. |
| textured_mesh | boolean | No | false | - | If set true, textured mesh will be generated and the price charged would be 3 times that of white mesh. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "hunyuan-3d-v2-1",
  "input": {
    "input_image_url": "https://storage.googleapis.com/magicpoint/inputs/hunyuan-3d-v2.1-input.png"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "object",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**hunyuan-3d-v2-1 — Image-to-3D AI Model**

Developed by Tencent as part of the **hunyuan-3d** family, **hunyuan-3d-v2-1** (also known as Hunyuan3D 2.1) is a scalable 3D asset generation system that transforms single images or text prompts into high-resolution, textured 3D models with Physically-Based Rendering (PBR) materials. This **image-to-3d AI model** solves the challenge of rapid 3D prototyping by delivering realistic, production-ready assets in minutes, accessible via online demos or local setups on NVIDIA GPUs with just 8GB VRAM. Ideal for creators seeking **Tencent image-to-3d** tools, it stands out with its open-source core and community optimizations for consumer hardware.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.