# Topaz Precision image upscale

Needs image url. Served by fal.ai.

Topaz Precision, image upscale, served by fal.ai. The OpenAPI schema for the topaz/upscale/image/precision queue. Price: $0.08 per started 24 megapixels of output (input size times the square of the upscale factor), measured on the rendered image after the call; the reservation is the bound you declare and the difference is refunded. Waits up to 40 s for the result; if the generation takes longer, the run stays RUNNING and returns a request_id; poll fal/status and fetch fal/result with model "topaz/upscale" and that request_id. Billed once, when the result is ready; a generation that fails is refunded.

- Tool ID: `fal/topaz-upscale-precision`
- Name in the catalog: Topaz Precision, image upscale
- Provider: [fal.ai](/providers/fal.md)
- Capability: [Image upscaling](/tools/image-generation/upscale.md)
- Price: $0.08 per unit
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_unit",
  "amountUsd": 0.08,
  "unitsPath": "image",
  "unitsMeasure": "megapixels",
  "unitsProbe": "image",
  "unitsPer": 24,
  "fractional": false,
  "maxUnits": 10,
  "maxUnitsField": "max_megapixels"
}
```

Pricing source: [https://fal.ai/models/topaz/upscale/image/precision](https://fal.ai/models/topaz/upscale/image/precision). $0.08 per started 24 megapixels of output (input size times the square of the upscale factor), measured on the rendered image after the call; the reservation is the bound you declare and the difference is refunded..

Price verification date: 2026-10-08.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "output_format": {
      "title": "Output Format",
      "enum": [
        "jpeg",
        "png"
      ],
      "description": "Output format of the upscaled image.",
      "type": "string",
      "default": "jpeg"
    },
    "strength": {
      "type": "number",
      "minimum": 0.01,
      "maximum": 1,
      "title": "Strength",
      "description": "Enhancement strength (0.01-1.0). Applies to Text Refine model only."
    },
    "face_enhancement_creativity": {
      "title": "Face Enhancement Creativity",
      "description": "Creativity level for face enhancement. 0.0 means no creativity, 1.0 means maximum creativity. Ignored if face enhancement is disabled.",
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 0
    },
    "subject_detection": {
      "title": "Subject Detection",
      "enum": [
        "All",
        "Foreground",
        "Background"
      ],
      "description": "Subject detection mode for the image enhancement.",
      "type": "string",
      "default": "All"
    },
    "image_url": {
      "title": "Image Url",
      "description": "Url of the image to be upscaled",
      "minLength": 1,
      "type": "string"
    },
    "face_enhancement_strength": {
      "title": "Face Enhancement Strength",
      "description": "Strength of the face enhancement. 0.0 means no enhancement, 1.0 means maximum enhancement. Ignored if face enhancement is disabled.",
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 0.8
    },
    "denoise": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "title": "Denoise",
      "description": "Denoising level (0.0-1.0). Default varies by model."
    },
    "sharpen": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "title": "Sharpen",
      "description": "Sharpening level (0.0-1.0). Default varies by model."
    },
    "face_enhancement": {
      "title": "Face Enhancement",
      "description": "Whether to apply face enhancement to the image.",
      "type": "boolean",
      "default": true
    },
    "fix_compression": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "title": "Fix Compression",
      "description": "Compression artifact removal level (0.0-1.0). Not supported by the CGI model."
    },
    "upscale_factor": {
      "title": "Upscale Factor",
      "description": "Factor to upscale the image by (e.g. 2.0 doubles width and height)",
      "type": "number",
      "minimum": 1,
      "maximum": 4,
      "default": 2
    },
    "model": {
      "title": "Model",
      "enum": [
        "Standard V2",
        "High Fidelity V3",
        "High Fidelity V2",
        "Low Resolution V2",
        "CGI",
        "Text Refine",
        "Faces"
      ],
      "description": "Precision upscaling model. Standard V2 fits most photos; High Fidelity V3/V2 preserve detail in professional shots; Low Resolution V2 recovers compressed sources; CGI targets art and rendered graphics; Text Refine keeps text and shapes crisp; Faces restores facial detail with Face Recovery 3.",
      "type": "string",
      "default": "Standard V2"
    },
    "crop_to_fill": {
      "title": "Crop To Fill",
      "type": "boolean",
      "default": false
    },
    "max_megapixels": {
      "type": "number",
      "minimum": 1,
      "maximum": 240,
      "default": 24,
      "description": "Upper bound of the output megapixels, in megapixels (default 24, max 240). The reservation is this bound at the unit price; after the call the megapixels fal meters are billed and the rest is refunded. Declare at least the real amount: a larger input is still processed but is never billed above the reservation."
    }
  },
  "required": [
    "image_url"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "fal/topaz-upscale-precision",
  "input": {
    "image_url": "https://storage.googleapis.com/falserverless/model_tests/codeformer/codeformer_poor_1.jpeg",
    "upscale_factor": 2,
    "max_megapixels": 24
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

This tool uses deferred settlement. Follow its returned task/run instructions; preserve the existing reservation until the result is reconciled.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://fal.ai/models/topaz/upscale/image/precision)

[REST inspection](https://api.agentik.cc/v1/tools/fal/topaz-upscale-precision) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/fal/topaz-upscale-precision) · [Agent index](/llms.txt)