← REST APIREST endpoint

Clean up a messy address.

Free-text in, structured out. Fixes typos, expands abbreviations, infers missing fields, and scores confidence.

Get an API keySee the MCP tool
POST /v1/ai/parse-address
Why you need it

The problem this solves.

Customer data, radio transcripts, and incident reports arrive as messy strings. Generic regex parsers miss half the cases. parse_address is LLM-grounded address parsing: send up to 100 messy free-text addresses, get back structured components plus an audit trail of corrections, with per-row confidence for review queue routing.

What it does for you

What comes back in the response.

  • Up to 100 addresses per request.
  • Structured output: street, locality, postcode, region, country.
  • Fixes typos, expands abbreviations, infers missing fields.
  • Itemised correction audit trail per row.
  • Use as a pre-step before geocode or batch_geocode to lift match rates.
Built for
For SAR teamsFor public-safety GISFor AI developersFor integrators
Try it

Call it from your backend.

Predictable HTTP. JSON in, JSON out. One auth header. Use it from any backend, edge function, or script.

Read the full reference
POST /v1/ai/parse-address
curl -X POST https://api.footstep.ai/v1/ai/parse-address \
  -H "x-api-key: sk_live_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{ ... }'

Related capabilities.

geocode

Turn an address, landmark, or place name into coordinates. Returns ranked candidates with confidence scores.

batch_geocode

Run up to 1,000 addresses through geocoding in a single call. Returns coordinates and confidence for each.

reverse_geocode

Given a coordinate, return the address or place label. Useful for labelling pins and incident reports.

Ready to call it?

£5 free credit on signup. One auth header, every major runtime.

Get an API keySee the MCP tool