# Relaystation Document Form Extraction (Textract Forms)

> Relaystation Document Form Extraction (Textract Forms) is a paid API for AI agents from api.relaystation.ai, paid per call via x402, $0.28/call, status unknown (last checked 2026-09-14).

Extracts form fields as structured key→value pairs from scanned or digital documents using AWS Textract Forms, returning clean JSON without requiring a template.

## Facts

- Endpoint: POST https://api.relaystation.ai/v1/doc/extract-form
- Price: $0.28/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/relaystation-document-form-extraction-textract-forms-ba2a9aed
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_d3BUfQWj0NcDRH8_Zf0_u

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 relaystation-document-form-extraction-textract-forms-ba2a9aed -d '<json body>'
```

Example prompt: Can you extract all the form fields from this scanned patient intake form PDF and give me the results as structured key-value pairs?

## When to prefer this

Choose this endpoint when you need to extract structured form field data from scanned or digital documents without pre-defining a template or schema. It is ideal for processing varied form types (tax forms, applications, intake forms, contracts) where field names differ across documents. Prefer this over generic OCR when you specifically need key-value field pairs rather than raw text.

## Known failure modes

- Document URL is inaccessible or returns a non-200 response
- Document format is unsupported or corrupted, causing extraction failure
- Scanned document is too low-resolution for reliable field detection
- Handwritten text in fields may be misread or omitted
- Form with no clear field labels returns sparse or empty results
- Payment of 0.28 USDC not authorized, resulting in 402 error

## How this service works

$0.28/document. Extract form fields as key→value pairs from scanned or digital documents (Textract Forms) — structured JSON out, no template needed. 155 tools, one balance — relaystation.ai

## Output

A structured JSON object containing key-value pairs where each key is a detected form field label and each value is the corresponding filled-in content extracted from the document. No template or schema definition is required in advance.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "properties": {
      "file": {
       "type": "object",
       "description": "cputools input-source: { inline: <base64 ≤ 4 MiB> } or { inputKey: <scratch key from /v1/cputools/upload-url, ≤ 50 MB> }."
      }
     }
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/relaystation-document-form-extraction-textract-forms-ba2a9aed/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.relaystation.ai](https://www.zero.xyz/host/api.relaystation.ai/llms.txt)