AIDataParser

Extract clean, schema-guaranteed JSON from a PDF or image. Provide the document via `url` or `base64`. Pass an optional JSON `schema` to constrain the output shape, and `instructions` to guide extraction. Returns the extracted data plus a confidence score and a review_needed flag. Costs 1 credit per successful call.

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "Public http(s) URL of the PDF or image to parse."
    },
    "base64": {
      "type": "string",
      "description": "Base64-encoded document bytes (alternative to `url`). Provide `media_type` alongside it."
    },
    "media_type": {
      "type": "string",
      "description": "MIME type for `base64` input, e.g. application/pdf, image/png, image/jpeg."
    },
    "schema": {
      "type": "object",
      "description": "Optional JSON Schema describing the exact output shape you want. When provided, the returned `data` conforms to it."
    },
    "schema_id": {
      "type": "string",
      "description": "Optional named template to use instead of a hand-written schema, e.g. \"invoice\", \"receipt\", \"resume\". Call the list_schemas tool for the full set. Ignored when `schema` is provided."
    },
    "instructions": {
      "type": "string",
      "description": "Optional natural-language guidance for what to extract."
    },
    "redact": {
      "type": "boolean",
      "description": "When true, PII (emails, SSNs, card numbers, phones, etc.) is masked in the output before it leaves the server."
    }
  }
}

Extract clean, schema-guaranteed JSON from raw/messy text you already have — scraped web content, email bodies, chat logs, OCR output, or pasted tables. Pass the text in `text`. Use this instead of parse_document when you don't have a file. Optional JSON `schema` (or `schema_id`) constrains the output shape and `instructions` guides extraction. Returns the extracted data plus a confidence score and a review_needed flag. Costs 1 credit per successful call.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The raw text to extract structured data from."
    },
    "schema": {
      "type": "object",
      "description": "Optional JSON Schema describing the exact output shape you want. When provided, the returned `data` conforms to it."
    },
    "schema_id": {
      "type": "string",
      "description": "Optional named template to use instead of a hand-written schema, e.g. \"invoice\", \"receipt\", \"resume\". Call the list_schemas tool for the full set. Ignored when `schema` is provided."
    },
    "instructions": {
      "type": "string",
      "description": "Optional natural-language guidance for what to extract."
    },
    "redact": {
      "type": "boolean",
      "description": "When true, PII (emails, SSNs, card numbers, phones, etc.) is masked in the output before it leaves the server."
    }
  },
  "required": [
    "text"
  ]
}

Given one sample document's `text`, propose a reusable JSON Schema for that document type. Use this when no built-in schema_id fits: infer a schema once, review it, then reuse it as `schema` on parse_document / parse_text across many documents for consistent output. Returns the JSON Schema plus a flat field list and an inferred doc_type. Costs 1 credit per successful call.

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "A single representative sample of the document type, as text."
    },
    "doc_type": {
      "type": "string",
      "description": "Optional hint for what kind of document this is, e.g. \"purchase order\", \"lab report\"."
    },
    "instructions": {
      "type": "string",
      "description": "Optional guidance on which fields matter or how to shape the schema."
    }
  },
  "required": [
    "text"
  ]
}

Check whether a JSON object conforms to a JSON `schema` (or a built-in `schema_id` template) and get back a valid flag plus per-field errors. Use this to verify data you already hold — a prior parse result, your own output, or an upstream feed — before acting on it or spending a credit. Deterministic, free, and needs no API key.

{
  "type": "object",
  "properties": {
    "data": {
      "description": "The JSON value to validate."
    },
    "schema": {
      "type": "object",
      "description": "JSON Schema to validate against. Takes precedence over schema_id."
    },
    "schema_id": {
      "type": "string",
      "description": "Built-in template id to validate against instead of a hand-written schema (invoice, receipt, resume, etc.). Call list_schemas for the full set."
    }
  },
  "required": [
    "data"
  ]
}

Return the number of extraction credits remaining on the authenticated API key. Free — does not consume a credit.

{
  "type": "object",
  "properties": {}
}

Return the built-in schema templates you can pass to parse_document as `schema_id` (invoice, receipt, resume, etc.), each with its id and the fields it extracts. Free — does not consume a credit and needs no API key.

{
  "type": "object",
  "properties": {}
}