---
title: "Use Topaz in OpenClaw via RunAPI — AI Image Upscaling API Guide"
url: "https://runapi.ai/openclaw-topaz.md"
canonical: "https://runapi.ai/openclaw-topaz"
locale: "en"
model: "topaz"
---

# Use Topaz in OpenClaw.

Topaz by Topaz Labs upscales images up to 8x resolution using neural networks that recover detail without artifacts. OpenClaw agents call it through the same RunAPI key used for chat and image generation — send an image URL, pick a scale factor, and poll for the enhanced result.

## API example

```bash
curl -X POST https://runapi.ai/api/v1/topaz/upscale_image \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "topaz-upscale-image",
    "image_url": "https://example.com/photo.jpg",
    "scale": 4
  }'

```

### Response

```json
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "topaz-upscale-image"
}

```

## How it works

1. **Configure RunAPI** — If you have not set up RunAPI in OpenClaw yet, follow the OpenClaw setup guide. Set the RUNAPI_API_KEY environment variable and add RunAPI as an OpenAI-compatible provider with baseUrl https://runapi.ai/v1.
2. **Call Topaz upscale_image** — Send a POST request to the upscale_image endpoint with model set to topaz-upscale-image, the source image_url, and an optional scale factor of 2, 4, or 8. The same RunAPI key handles authentication.
3. **Poll for the result** — The endpoint returns a task_id with status pending. Poll the task status endpoint until the status changes to completed, then retrieve the upscaled image URL from the response. RunAPI SDKs and the CLI handle polling automatically.

## Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | `string` | Required. topaz-upscale-image or topaz-upscale-video. |
| `image_url` | `string` | URL of the image to upscale. |
| `scale` | `integer` | Optional. Upscale factor: 2, 4, or 8. Default 2. |
| `callback_url` | `string` | Optional. Webhook URL for async completion notification. |

## FAQ

### Can I use Topaz in OpenClaw?

Yes. Configure RunAPI as an OpenAI-compatible provider in OpenClaw, then instruct the agent to call the Topaz upscale_image endpoint. The same RUNAPI_API_KEY used for chat and image generation also handles upscaling requests.

### Do I need a separate API key for Topaz?

No. The same RUNAPI_API_KEY that powers chat, image generation, and other models also works for Topaz upscaling. All RunAPI models share one API key and one credits balance.

### Is Topaz upscaling async or sync?

Topaz upscaling is async. The endpoint returns a task_id immediately. Your OpenClaw agent polls the task status endpoint until the upscaled image is ready. RunAPI SDKs and the CLI handle polling automatically.

### What does Topaz upscaling cost?

Topaz uses pay-as-you-go per-task pricing through RunAPI. Check the RunAPI pricing page for current rates. There is no monthly subscription or minimum spend -- unlike the $199/year Topaz desktop app subscription.

### How does Topaz upscaling compare to Recraft upscaling on RunAPI?

Topaz offers configurable 2x/4x/8x scale factors and excels at photographic detail at extreme enlargements. Recraft crisp upscale is optimized for clean edge recovery on design assets with lower per-task cost. For product photos and design work, try Recraft first. For maximum resolution photography, use Topaz.

### Does quality degrade on certain image types?

Topaz works best on photographic content. Heavily compressed images, very small source files, or images with existing AI artifacts may produce results that look plasticky or over-smoothed at high scale factors. Start with 2x to test quality before committing to 4x or 8x on a batch.


## Links

- [OpenClaw setup guide →](https://runapi.ai/openclaw)
- [Topaz models →](https://runapi.ai/models/topaz)
- [Model catalog](https://runapi.ai/models)
- [API docs](https://runapi.ai/docs)