# Satellite Before/After Comparison (NASA GIBS)

> Satellite Before/After Comparison (NASA GIBS) is a paid API for AI agents from agentsvc.io, paid per call via x402, $0.013/call, status unknown (last checked 2026-10-12).

Generates a side-by-side JPEG comparing NASA satellite imagery of the same location on two dates, with pixel-level change metrics and a plain-language assessment of whether changes are real or weather-related.

## Facts

- Endpoint: POST https://agentsvc.io/api/v1/proxy/satellite-compare?utm_source=zero.xyz
- Price: $0.013/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/satellite-before-after-comparison-nasa-gibs-ab76984b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_knhvf-IzvHA6cYcSEY1LQ

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 satellite-before-after-comparison-nasa-gibs-ab76984b -d '<json body>'
```

Example prompt: Show me a before-and-after satellite comparison of Maui, Hawaii — use MODIS Terra imagery with a 75 km radius, comparing August 7 2023 (after the wildfires) against August 7 2022, and tell me whether the change looks real or just cloud cover.

## When to prefer this

Choose this endpoint when you need a quick, visually interpretable before-and-after comparison of a geographic area using freely available NASA satellite data, especially for event-driven change detection (wildfires, floods, hurricanes, deforestation). It is ideal when you want both a shareable image and quantitative change metrics without needing commercial high-resolution imagery. Prefer it over single-image satellite endpoints when temporal comparison is the core need, and over full GIS pipelines when a lightweight, paid-per-call, no-infrastructure approach is sufficient.

## Known failure modes

- Requested dates may have no available imagery (NASA GIBS archive gaps, especially for VIIRS before 2012)
- High cloud or snow coverage on one or both dates can make pixel-change metrics unreliable or mask real change
- Place name not found in GeoNames for small or ambiguous localities — use lat/lon instead
- Radius too large (>500 km) or too small (<5 km) will be rejected by schema validation
- Invalid date format or date_after earlier than date_before will cause an error
- MODIS resolution (~250 m/pixel) may not detect fine-scale changes in small areas

## How this service works

86 APIs for AI agents: web scraping and crawling to Markdown, AI summaries, data extraction and cited answers, screenshots and PDF, PDF, OCR and document conversion, news, paper and developer search and more, paid per call with USDC on Base, Solana, Polygon or Arbitrum via x402. No account, no API key, free sample on every service.

## Output

Returns a composite JPEG image (2× requested width + 8 px) showing the two dates side by side with date labels overlaid, plus JSON metrics including the share of changed pixels, overall brightness change, cloud/haze/snow coverage estimates for each date, and a plain-language interpretation stating whether the detected change is likely real environmental change or attributable to atmospheric conditions like clouds or snow.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "lat": {
   "type": "number"
  },
  "lon": {
   "type": "number"
  },
  "bbox": {
   "type": "array",
   "items": {
    "type": "number"
   },
   "maxItems": 4,
   "minItems": 4
  },
  "layer": {
   "enum": [
    "modis_terra",
    "modis_aqua",
    "viirs_snpp",
    "viirs_noaa20"
   ],
   "type": "string",
   "default": "modis_terra"
  },
  "place": {
   "type": "string",
   "description": "Place name instead of coordinates, e.g. \"Valencia, Spain\" (GeoNames, cities and towns)"
  },
  "width": {
   "type": "integer",
   "default": 384,
   "maximum": 768,
   "minimum": 64,
   "description": "Width of each of the two images; the composite is 2 x width + 8 px"
  },
  "radius_km": {
   "type": "number",
   "default": 50,
   "maximum": 500,
   "minimum": 5
  },
  "date_after": {
   "type": "string",
   "description": "YYYY-MM-DD, default yesterday"
  },
  "date_before": {
   "type": "string",
   "description": "YYYY-MM-DD, default 365 days before date_after"
  },
  "include_separate": {
   "type": "boolean",
   "default": false,
   "description": "Also return both images separately as base64"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "data": {
   "bbox": {
    "max_lat": -18.2995,
    "max_lon": -66.6243,
    "min_lat": -19.2005,
    "min_lon": -67.5757
   },
   "note": "Daily true-color mosaics at about 250 m per pixel. Change metrics are compute...",
   "layer": "modis_terra",
   "width": 520,
   "change": {
    "after": {
     "no_data_pct": 0,
     "mean_brightness": 49.8,
     "cloud_or_snow_pct": 6.4,
     "cloud_haze_or_snow_pct": 18.3
    },
    "before": {
     "no_data_pct": 13,
     "mean_brightness": 42.6,
     "cloud_or_snow_pct": 0.5,
     "cloud_haze_or_snow_pct": 8.6
    },
    "reading": "Visible change in part of the area (for example water level, burn scars, floo...",
    "reliable": true,
    "changed_pixels_pct": 20.1,
    "mean_brightness_change_pct": 7.3
   },
   "height": 264,
   "layout": "side_by_side: left = date_before, right = date_after, date labels on top",
   "layer_id": "MODIS_Terra_CorrectedReflectance_TrueColor",
   "mime_type": "image/jpeg",
   "date_after": "2016-05-10",
   "size_bytes": 22150,
   "attribution": "NASA EOSDIS GIBS / Worldview",
   "date_before": "2014-05-10",
   "image_base64": "/9j/2wBDAAYEBAUEBAYFBQUG…"
  },
  "success": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/satellite-before-after-comparison-nasa-gibs-ab76984b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentsvc.io](https://www.zero.xyz/host/agentsvc.io/llms.txt)