> ## Documentation Index > Fetch the complete documentation index at: https://docs.landing.ai/llms.txt > Use this file to discover all available pages before exploring further. # ADE Parse > Parse a document and return the parse response inline. ## OpenAPI ````yaml /dpt3/openapi-adev2.json post /v2/parse openapi: 3.1.0 info: title: >- LandingAI Agentic Document Extraction (ADE) API v2: Parse and Extract Documents with DPT-3 description: >- Parse and extract data from documents with DPT-3, a document parsing model from LandingAI, using the Agentic Document Extraction (ADE) v2 endpoints. Parse converts PDFs and images into structured Markdown and elements with per-element grounding (page numbers and coordinates) for RAG, search, and extraction pipelines. Extract pulls specific fields from parsed Markdown using a JSON schema. Documentation: https://docs.landing.ai version: 1.0.0 servers: - url: https://api.ade.landing.ai description: Production vision tools API security: [] paths: /v2/parse: post: tags: - Parse summary: ADE Parse description: Parse a document and return the parse response inline. operationId: parse_run_sync requestBody: required: true content: multipart/form-data: schema: type: object properties: document: type: string format: binary description: >- The file to parse. The file must be a PDF or image; see the list of [supported file types](https://docs.landing.ai/dpt3/file-types). Provide either `document` or `document_url`, not both. document_url: type: string description: >- A publicly accessible URL to the file to parse. The file must be a PDF or image; see the list of [supported file types](https://docs.landing.ai/dpt3/file-types). Provide either `document` or `document_url`, not both. model: type: string description: >- The DPT-3 model snapshot to use for this request. Accepts a dated snapshot (for example, `dpt-3-pro-20260710`), the `dpt-3-pro-latest` alias, or the bare `dpt-3-pro` family name (equivalent to `dpt-3-pro-latest`). Defaults to the latest DPT-3 Pro snapshot. options: additionalProperties: false properties: pages: anyOf: - items: type: integer type: array - type: 'null' default: null title: Pages blocks: $ref: '#/components/schemas/BlocksOptions' atomic_grounding: default: true description: >- Include the fine-grained `atomic_grounding` array on leaf elements. Set `false` to omit the field entirely from every node. title: Atomic Grounding type: boolean inline_markdown: default: false description: >- Include each node's slice of the document `markdown` inline as a `markdown` field on every structure node: the document root, each page, and each element (including table cells). `atomic_grounding` entries do not carry it. title: Inline Markdown type: boolean password: anyOf: - type: string - type: 'null' default: null description: >- Password for encrypted PDFs. Not currently supported — providing a value returns a 422 error; decrypt the file before uploading. title: Password title: ParseOptions type: object description: >- Optional object that customizes the parse. Use it to select which pages to process, adjust how content appears in the Markdown, or control how much detail the response includes. Sent as a JSON-serialized string in form data. responses: '200': description: The parse response content: application/json: schema: $ref: '#/components/schemas/ParseResponse' '206': description: Partial success (some pages failed to parse) content: application/json: schema: $ref: '#/components/schemas/ParseResponse' '422': description: Request validation failed. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' x-codeSamples: - lang: cURL label: cURL source: |- curl -X POST 'https://api.ade.landing.ai/v2/parse' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -F 'document=@document.pdf' \ -F 'model=dpt-3-pro-latest' - lang: Python label: Python source: >- import requests url = 'https://api.ade.landing.ai/v2/parse' headers = {'Authorization': 'Bearer YOUR_API_KEY'} files = {'document': open('document.pdf', 'rb')} data = {'model': 'dpt-3-pro-latest'} response = requests.post(url, headers=headers, files=files, data=data) print(response.json()) - lang: JavaScript label: Node.js source: |- const axios = require('axios'); const FormData = require('form-data'); const fs = require('fs'); const form = new FormData(); form.append('document', fs.createReadStream('document.pdf')); form.append('model', 'dpt-3-pro-latest'); axios.post('https://api.ade.landing.ai/v2/parse', form, { headers: { 'Authorization': 'Bearer YOUR_API_KEY', ...form.getHeaders() } }) .then(response => console.log(response.data)) .catch(error => console.error(error)); components: schemas: BlocksOptions: additionalProperties: false properties: text: $ref: '#/components/schemas/BaseElementOptions' table: $ref: '#/components/schemas/TableOptions' figure: $ref: '#/components/schemas/FigureOptions' marginalia: $ref: '#/components/schemas/BaseElementOptions' attestation: $ref: '#/components/schemas/BaseElementOptions' logo: $ref: '#/components/schemas/BaseElementOptions' scan_code: $ref: '#/components/schemas/BaseElementOptions' card: $ref: '#/components/schemas/BaseElementOptions' title: BlocksOptions type: object ParseResponse: description: |- The parse result: the full document as `markdown`, its hierarchical `structure` (with per-node spatial `grounding` inline), and request `metadata`. properties: markdown: description: The full document as a single Markdown string, in reading order. title: Markdown type: string metadata: $ref: '#/components/schemas/ParseMetadata' description: >- Information about the request: model version, page count, duration, billing, and more. structure: $ref: '#/components/schemas/Document' description: >- The document's hierarchical structure: pages and the elements detected on each page. Every node below the root carries its spatial data inline in a `grounding` object (`{page, range, box}`, normalized page coordinates); leaf elements additionally carry `atomic_grounding`. required: - markdown - metadata - structure title: ParseResponse type: object ErrorResponse: type: object title: ErrorResponse required: - code - message properties: code: type: string description: >- Stable snake_case error code (e.g. ``validation_error``, ``unknown_model_version``, ``invalid_url``, ``invalid_api_key``, ``rate_limit_exceeded``). message: type: string description: Human-readable detail. BaseElementOptions: additionalProperties: false properties: markdown: default: true title: Markdown type: boolean title: BaseElementOptions type: object TableOptions: additionalProperties: false properties: markdown: default: true title: Markdown type: boolean format: default: html enum: - markdown - html title: Format type: string title: TableOptions type: object FigureOptions: additionalProperties: false properties: markdown: default: true title: Markdown type: boolean title: FigureOptions type: object ParseMetadata: description: >- Information about a parse request. This is the customer-facing shape — the internal billing-canonical metadata (``aide_common.parse_schema.ParseMetadata``) is projected into it at the render boundary (``project_customer_metadata``). properties: job_id: anyOf: - type: string - type: 'null' description: >- The parse job identifier — always server-minted and unique per submit. On the async `/jobs` route this is the id the caller polls. Correlates with the job's entry in your billing dashboard. Format: ``-<26-character Crockford base32 ULID>`` matching ``^(parse|extract)-[0-9a-hjkmnp-tv-z]{26}$``. Opaque, server-minted, and stable for the life of the job — the same id is returned on the sync response, the async 202, and every poll. Treat it as opaque; older id formats remain accepted indefinitely and are never re-issued. title: Job Id model_version: anyOf: - type: string - type: 'null' description: >- The exact model snapshot that parsed the document, e.g. `dpt-3-pro-20260710`. title: Model Version page_count: anyOf: - type: integer - type: 'null' description: >- Total number of pages in the source document. Includes pages filtered out by `options.pages`; the actual returned pages are in `structure.children`. title: Page Count output_markdown_chars: anyOf: - type: integer - type: 'null' description: Number of Unicode code points in the returned `markdown` string. title: Output Markdown Chars range_units: const: unicode_codepoints description: >- Units of every `range` offset in the response. Always `"unicode_codepoints"` (Unicode code points into `markdown`). Declared explicitly so consumers know how to slice the string — e.g. JavaScript strings are UTF-16, so a naive `.slice()` drifts when the markdown contains astral characters; such consumers must convert code-point offsets to UTF-16 indices first. title: Range Units type: string openapi_spec: description: >- URL of the OpenAPI spec covering this API, for inspection and client generation. title: Openapi Spec type: string failed_pages: description: >- 1-indexed page numbers that failed to parse. Empty when all pages succeed; failed pages also appear in `structure.children` with `status: failed`. items: type: integer title: Failed Pages type: array duration_ms: anyOf: - type: integer - type: 'null' description: Total processing time in milliseconds. title: Duration Ms billing: $ref: '#/components/schemas/ParseBilling' description: 'Billing summary: the service tier and the credits charged.' required: - job_id - model_version - page_count - output_markdown_chars - range_units - openapi_spec - failed_pages - duration_ms - billing title: ParseMetadata type: object Document: properties: type: const: document default: document description: >- The node type. Identifies this node as the root of the structure tree. title: Type type: string children: description: The pages of the document, in source order. items: $ref: '#/components/schemas/Page' title: Children type: array markdown: anyOf: - type: string - type: 'null' default: null description: >- The full document markdown — identical to the top-level `markdown` field, included so the structure tree is self-contained. Present only when `options.inline_markdown` is `true`. title: Markdown title: Document type: object ParseBilling: description: Billing summary for one parse request. properties: service_tier: anyOf: - enum: - standard - priority type: string - type: 'null' description: >- The service tier the request ran in: `standard` or `priority`. A sync request reports `priority` (same lane, same price). title: Service Tier total_credits: anyOf: - type: number - type: 'null' description: Credits charged for this request. title: Total Credits required: - service_tier - total_credits title: ParseBilling type: object Page: properties: type: const: page default: page description: The node type. Identifies this node as a page in the structure tree. title: Type type: string grounding: $ref: '#/components/schemas/Grounding' description: >- The page's spatial data: `page` is the 1-indexed page number in the source document (not contiguous when `options.pages` filters out some pages); `range` covers this page's content in the top-level `markdown` string (zero-length `start == end` for failed pages); `box` is always the full page `{0, 0, 1, 1}`. status: default: ok description: >- Whether this page was parsed successfully (`ok`) or failed (`failed`). enum: - ok - failed title: Status type: string reason: anyOf: - type: string - type: 'null' default: null description: Failure reason. Present only when `status` is `failed`. title: Reason children: description: >- The elements detected on this page, in reading order. Empty for failed pages. items: $ref: '#/components/schemas/Element' title: Children type: array markdown: anyOf: - type: string - type: 'null' default: null description: >- This page's slice of the top-level `markdown` string (`markdown[grounding.range.start:grounding.range.end]`). `""` for failed pages. Present only when `options.inline_markdown` is `true`. title: Markdown required: - grounding title: Page type: object Grounding: description: |- Where a node lives: its page, its slice of `markdown`, and its box. The same shape is used for page nodes, element nodes, and each `atomic_grounding` entry, so any grounding object is self-contained — it can be lifted out of the tree and still locates its content. properties: page: description: >- 1-indexed page number this grounding is on. On a page node, the page's own number. title: Page type: integer range: $ref: '#/components/schemas/Range' description: >- `[start, end)` offsets into the top-level `markdown` string covered by this node or segment. box: $ref: '#/components/schemas/Box' description: >- Bounding box in normalized page coordinates (`0`–`1` fractions of page width/height, at most 8 decimal places). A page node's box is always the full page `{0, 0, 1, 1}`. required: - page - range - box title: Grounding type: object Element: description: |- Hierarchical document element. All non-page elements share this shape. Keys off `type`; optional fields are excluded from the serialized JSON via ``exclude_none=True`` when not set. properties: type: description: >- The element type. Determines which optional fields appear on this element. enum: - text - table - table_cell - figure - marginalia - attestation - logo - card - scan_code title: Type type: string id: description: >- Semantic element id, unique within the document. Format `-`, where `` is a per-type 0-based counter assigned in reading order — `text-0` is the first text element in the document, `figure-0` the first figure, `table_cell-0` the first cell of the first table. Stable within a response but not across re-parses of the same document. title: Id type: string grounding: $ref: '#/components/schemas/Grounding' description: >- The element's spatial data: the page it appears on, its `[start, end)` range in the top-level `markdown` string, and its bounding box in normalized page coordinates. atomic_grounding: anyOf: - items: $ref: '#/components/schemas/Grounding' type: array - type: 'null' default: null description: >- Fine-grained grounding segments at the model's current granularity (visual lines today; finer in future versions, same schema). Present only on leaf elements — every type except `table`. `[]` only when segments are structurally impossible: `table_cell` (a cell has no finer granularity than itself) and elements whose markdown is suppressed via `blocks..markdown=false`. Any other leaf the model could not segment finer carries a single entry covering the element's full range and box. Omitted entirely when `options.atomic_grounding` is `false`. title: Atomic Grounding children: anyOf: - items: $ref: '#/components/schemas/Element' type: array - type: 'null' default: null description: >- The cells (`table_cell` elements) of a `table` element. Present only when `type` is `table`. title: Children markdown: anyOf: - type: string - type: 'null' default: null description: >- The element's slice of the top-level `markdown` string (`markdown[grounding.range.start:grounding.range.end]`). `""` for zero-length ranges (e.g. blocks suppressed via `blocks..markdown=false`). Present only when `options.inline_markdown` is `true`. title: Markdown row: anyOf: - type: integer - type: 'null' default: null description: >- 0-indexed row position of this cell within its parent `table`. Present only on `table_cell` elements. title: Row col: anyOf: - type: integer - type: 'null' default: null description: >- 0-indexed column position of this cell within its parent `table`. Present only on `table_cell` elements. title: Col colspan: anyOf: - type: integer - type: 'null' default: null description: >- Number of columns this cell spans. `1` for unmerged cells. Present only on `table_cell` elements. title: Colspan rowspan: anyOf: - type: integer - type: 'null' default: null description: >- Number of rows this cell spans. `1` for unmerged cells. Present only on `table_cell` elements. title: Rowspan required: - type - id - grounding title: Element type: object Range: description: A `[start, end)` slice of the top-level `markdown` string. properties: start: description: >- Inclusive start offset into the top-level `markdown` string, in the units declared by `metadata.range_units` (Unicode code points). title: Start type: integer end: description: >- Exclusive end offset into the top-level `markdown` string, in the units declared by `metadata.range_units` (Unicode code points). title: End type: integer required: - start - end title: Range type: object Box: description: >- Axis-aligned bounding box in normalized page coordinates. Every value is a fraction of the page's width (`xmin`/`xmax`) or height (`ymin`/`ymax`) in `[0, 1]`, with at most 8 decimal places. To convert to pixels, multiply by the dimensions of whatever raster of the page you are drawing on. Coordinates are clamped and rounded at construction so the in-process value always equals the serialized one. properties: xmin: description: Left edge as a fraction of the page width, in `[0, 1]`. title: Xmin type: number ymin: description: Top edge as a fraction of the page height, in `[0, 1]`. title: Ymin type: number xmax: description: Right edge as a fraction of the page width, in `[0, 1]`. title: Xmax type: number ymax: description: Bottom edge as a fraction of the page height, in `[0, 1]`. title: Ymax type: number required: - xmin - ymin - xmax - ymax title: Box type: object ````