> ## 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.
# Changelog
> Learn about updates and new features across the ADE v2 APIs: Parse, Extract, Parse Jobs, and Extract Jobs.
export const ade = 'Agentic Document Extraction';
export const dpt2 = 'DPT-2';
export const dpt3pro = 'DPT-3 Pro';
export const dpt3 = 'DPT-3';
export const parseJobs = 'Parse Jobs';
export const parseDpt3 = 'Parse';
export const parse = 'ADE Parse';
This release updates the [Parse v2 API](./parse) and adds three new {ade} v2 APIs.
In this release:
* [Parse v2 API updates](#parse-v2-api-updates)
* [Parse Jobs v2](#parse-jobs-v2)
* [Extract v2 API](#extract-v2-api)
* [Extract Jobs v2](#extract-jobs-v2)
* [Service Tiers for Jobs](#service-tiers-for-jobs)
* [New Playground URL](#new-playground-url)
* [Redesigned Usage page](#redesigned-usage-page)
## Parse v2 API Updates
We have updated the [Parse v2 API](./parse), powered by our newest parsing model, {dpt3}.
The Parse v2 API is a complete rethink of document parsing for the era of AI agents and agentic workflows: a hierarchical response shape, line-level visual grounding, cleaner Markdown, and complexity-aware pricing. Calls go to the `/v2/parse` endpoint.
Get started with the [Quickstart](./quickstart).
### Parse API Changes
The Parse v2 API has several changes. If you built against it before July 7, review these:
* **Bounding boxes and page dimensions are now always in pixels.** Previously, PDF coordinates were returned in points and image coordinates in pixels. The per-page `unit` field is removed from the response. A new [`dpi` option](./parse-input#request-options) (default 200, range 72 to 300) controls how PDF coordinates scale to pixels (`pixels = PDF points × dpi / 72`) and has no effect on image inputs. Each PDF page reports the `dpi` used, so you can re-render the page at a matching resolution and have the boxes line up.
* **The `options.elements` field is renamed to `options.blocks`.** The option that controls per-element captions and table format has a new name. For example, use `options.blocks.table.format` instead of `options.elements.table.format`. Update any requests that set these options.
* **Table cells use a single `table_cell` type.** The separate `td` and `th` element types are merged into one `table_cell` type. Header and data cells are no longer distinguished by type.
* **The page break marker is now ``.** The previous `` comment is no longer emitted. Update any code that splits the Markdown on the page marker.
* **Parse output ends with a document ID marker.** The Markdown now appends `` as its final line. The [Extract v2 API](./extract) reads this automatically to link an extraction back to the parse job it came from.
* **The `grounding` field is now a tree that mirrors `structure`.** Previously, grounding was a flat object keyed by block `id`. It is now a `document → page → block` tree with the same order and `id`s as `structure`: each block node repeats its `id` and `span` and adds `box` and `parts`, a `table` node nests its cells' grounding as `children`, and the per-block `page` field is removed (the page number lives on the page node). Walk the two trees together, or index the grounding nodes by `id`. See [Grounding](./parse-response#grounding-where-things-are).
* **The response `metadata` block has a new shape.** The `filename` field is removed, `version` is renamed to `model_version`, and `credit_usage` is replaced by `billing.total_credits`. The new `billing.service_tier` field reports the service tier. See [Metadata](./parse-response#metadata).
* **Visual blocks have a new Markdown format.** Figures render as HTML-style `...` elements containing transcribed text and generated `` blocks, instead of image tags. Attestations emit a bracketed label line such as `[SIGNED]` followed by the transcribed text, and logos and scan codes render as transcribed text with short bracketed labels. See [Figure and Attestation Labels](./parse-response#figure-and-attestation-labels).
* **Math formulas are transcribed as LaTeX.** Inline math is wrapped in `$...$` and display math in `$$...$$`. The `` and `` tags now apply only to superscript and subscript text that is not part of a math formula.
* **The v2 APIs are served only from `api.ade.landing.ai`.** Code samples copied from the Playground early in the Preview (before June 3) point at an earlier host and path that no longer serve the v2 APIs. Update those requests to `https://api.ade.landing.ai/v2/parse`.
* **Documents over the size cap now return HTTP 422.** The Parse v2 API previously returned HTTP 413 for a document over the 50 MiB limit. It now returns a 422 error with the same message. Update any error handling keyed to 413.
See [Parse Documents](./parse) for the full request and response details.
## Parse Jobs v2
The new [Parse Jobs v2](./parse-async) API parses documents asynchronously. Submit a document, receive a `job_id` immediately, and poll for the result instead of holding open a synchronous request. {parseJobs} runs the same parsing as the synchronous Parse API and returns the same Parse v2 response shape.
* **Submit and poll.** Create a job, then check its status and retrieve the result when it finishes.
* **Parse large documents.** Jobs accept up to 6,000 pages and 1 GiB per PDF (50 MiB for images).
* **Save output to your storage.** Write the parsed output directly to a URL you control with `output_save_url`.
See [Parse Asynchronously (Parse Jobs)](./parse-async).
## Extract v2 API
The new [Extract v2 API](./extract) pulls specific fields from a document with a JSON schema and returns the values in a structured, predictable format.
* **Schema-driven extraction.** Define the fields you want with a JSON schema and get consistent results across documents with varying layouts.
* **Span-level grounding.** Each extracted value includes `[start, end)` character offsets that map it back to its location in the source Markdown.
* **Works on Markdown from any source.** Extract from the Parse v2 API output, a third-party parser, or hand-authored Markdown.
Get started with [Extract Data](./extract).
## Extract Jobs v2
The new [Extract Jobs v2](./extract-async) API runs long-running extractions asynchronously. Submit the Markdown and schema, receive a `job_id`, and poll for the result. Use it for long documents or large, complex schemas.
See [Asynchronous Extraction (Extract Jobs)](./extract-async).
## Service Tiers for Jobs
Parse Jobs and Extract Jobs both let you choose a service tier when you create a job:
* **Standard tier.** Consumes half the credits of the priority tier, with a slower turnaround. Best for cost-sensitive or non-urgent workloads.
* **Priority tier.** Consumes credits at the full rate, the same as synchronous processing, with a faster turnaround. Best for time-sensitive jobs.
Jobs run on the `standard` tier unless you set the `service_tier` field to `priority` when you create the job.
Every v2 response reports the tier the request ran on and the credits it consumed in `metadata.billing` (`service_tier` and `total_credits`). Synchronous requests always report the `priority` tier.
## New Playground URL
The {ade} Playground is now available at [ade.landing.ai](https://ade.landing.ai/) in the US and at [ade.eu-west-1.landing.ai](https://ade.eu-west-1.landing.ai) in the EU. We've moved away from `va.landing.ai` to reflect our commitment to {ade} (ADE).
Links to the previous URL continue to work through automatic redirects, so no action is required. We still recommend updating any saved bookmarks to the new URL.
## Redesigned Usage Page
The [Usage page](https://ade.landing.ai/settings/usage) makes it easier to see how your credits are consumed and why. It now shows:
* **Daily and monthly consumption** as a bar chart, so you can spot trends and spikes.
* **Detailed per-job logs** with new columns, including the job ID, the endpoint called, the model used (such as {dpt2} or {dpt3pro}), and the mode (Sync or Async), alongside the credits each job used.
For details, see [Monitor Credit Usage](../ade/ade-pricing#monitor-credit-usage).
## HTML Tables by Default
Tables now return as HTML instead of pipe-syntax Markdown. HTML preserves merged cells and nested layouts that pipe syntax cannot represent.
## Parse Options in the Playground
The Parse tab's **Config** menu now exposes {dpt3} parse options directly in the browser: choose which element types to caption, set the table output format, toggle fine-grained grounding, and select specific pages.
These controls map to the API's [`options`](./parse-input#request-options) field.
See [Parse in the Playground](./playground).
## Preview of DPT-3 and the New Parse API
{dpt3}, our newest parsing model, and the redesigned [{parseDpt3} API](https://docs.landing.ai/api-reference/parse/ade-parse) are now available in Preview. {dpt3} is a complete rethink of document parsing for the era of AI agents and agentic workflows: a new model architecture, a new response shape, and complexity-aware pricing.
Upload a document directly in the browser. No code required.
See parameters, response fields, and code samples.
### Highlights
* **Designed for agent systems.** Stable element ids, predictable hierarchy, and Markdown span pointers so AI agents can map results back to source.
* **Hierarchical layout model.** The structured output is a nested hierarchy: pages, elements on each page, lines within text elements, and cells within tables.
* **Line-level visual grounding.** Bounding boxes per element, plus per-line boxes for text elements.
* **Cleaner, more standardized Markdown.** Standard Markdown image syntax for visuals, structured attestations and scan codes, standardized checkboxes, and figure subtype labels.
* **New endpoint and response shape.** Calls go to the [new API](https://docs.landing.ai/api-reference/parse/ade-parse), with a hierarchical `structure` tree alongside a flat `grounding` map keyed by element id. See the [Migration Guide](./migration-guide).
### Get Started
* [Overview](./overview)
* [Quickstart](./quickstart)
* [Migration Guide from DPT-2](./migration-guide)
