Receipt Categorisation

Read a receipt and file it: supplier, date, amount, tax, currency, expense category and line items, ready for an expense report.

Pay by wallet (x402) AI-generated receipt-categorize

Example

Example answer

{
  "date": null,
  "category": "groceries",
  "currency": "USD",
  "subtotal": 6.48,
  "line_items": [
    {
      "amount": 2.99,
      "quantity": null,
      "unit_price": null,
      "description": "Milk"
    },
    {
      "amount": 3.49,
      "quantity": null,
      "unit_price": null,
      "description": "Bread"
    }
  ],
  "tax_amount": null,
  "tip_amount": null,
  "vendor_name": "Grocery store",
  "total_amount": 6.48,
  "card_last_four": null,
  "payment_method": null,
  "expense_report_fields": {
    "date": null,
    "amount": 6.48,
    "vendor": "Grocery store",
    "category": "groceries",
    "currency": "USD",
    "description": "Grocery store - Milk, Bread"
  }
}

Inputs

Field	Type	Required	What it is
`text`	string	No	—
`base64`	string	No	—
`image_url`	string	No	—

Output fields

How reliably each field appears in a successful answer.

Field	Type	Appears
`category`	string	Always (present in every successful answer)
`currency`	string	Always (present in every successful answer)
`line_items`	array	Always (present in every successful answer)
`vendor_name`	string	Always (present in every successful answer)
`total_amount`	number	Always (present in every successful answer)

How to call it

The same tool through each route. MCP clients reach it through Strale’s server at https://api.strale.io/mcp; the call below is what the agent sends.

# Needs an API key. max_price_cents caps what this call may cost.
curl -X POST https://api.strale.io/v1/do \
  -H "Authorization: Bearer $STRALE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "capability_slug": "receipt-categorize",
    "inputs": {
      "text": "Starbucks Coffee\nDate: 2024-01-15\nCaffe Latte x1 $5.50\nTotal: $5.50\nVisa ending 4242"
    },
    "max_price_cents": 5
  }'

{
  "tool": "strale_execute",
  "arguments": {
    "slug": "receipt-categorize",
    "inputs": {
      "text": "Starbucks Coffee\nDate: 2024-01-15\nCaffe Latte x1 $5.50\nTotal: $5.50\nVisa ending 4242"
    },
    "max_price_cents": 5
  }
}

import { Strale } from "straleio";

const strale = new Strale({ apiKey: process.env.STRALE_API_KEY! });
const result = await strale.do({
  capability_slug: "receipt-categorize",
  inputs: {
    "text": "Starbucks Coffee\nDate: 2024-01-15\nCaffe Latte x1 $5.50\nTotal: $5.50\nVisa ending 4242"
  },
  max_price_cents: 5,
});

import os
from straleio import Strale, DoRequest

strale = Strale(api_key=os.environ["STRALE_API_KEY"])
result = strale.do(DoRequest(
    capability_slug="receipt-categorize",
    inputs={
        "text": "Starbucks Coffee\nDate: 2024-01-15\nCaffe Latte x1 $5.50\nTotal: $5.50\nVisa ending 4242",
    },
    max_price_cents=5,
))

# No account. The first request answers 402 with the price in USDC;
# an x402 client pays it from your wallet and repeats the request.
curl -i 'https://api.strale.io/x402/v2/receipt-categorize?text=Starbucks+Coffee%0ADate%3A+2024-01-15%0ACaffe+Latte+x1+%245.50%0ATotal%3A+%245.50%0AVisa+ending+4242'

Limitations

Unusual or mixed purchases can be miscategorised
AI categorisation based on merchant name and amount — unusual merchants or multi-category purchases may be miscategorised
What to do instead: Provide your chart of accounts or category taxonomy in the input for more accurate categorisation
Input images are limited to 4 MiB decoded
Images supplied by URL or base64 are refused above 4 MiB of decoded data, with a caller_input error naming the input field and no charge. Resize or compress the image before submitting.