> ## Documentation Index
> Fetch the complete documentation index at: https://docs.reducto.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Release notes for the Reducto hosted API and Studio

<Update
  label="June 2026"
  rss={{
title: "June 2026 - New Deep Extract model, default model rollouts, Batch Queue, and legacy OCR retirement",
description: "June 2026 brings a new Deep Extract model, automatic mode for agentic tables, new default layout and agentic models, discounted Batch Queue processing, faster PDF rendering in Studio, and retirement of the legacy OCR option."
}}
>
  #### New Deep Extract model

  A new [Deep Extract](/configs/extract/deep-extract) model is available. It processes documents faster than the previous Deep Extract model and improves extraction accuracy. To use it, enable Deep Extract and set the Deep Extract model to `v2` in your request settings:

  ```json theme={null}
  {
    "settings": {
      "deep_extract": true,
      "alpha": {
        "deep_extract_model": "v2"
      }
    }
  }
  ```

  #### Automatic mode for agentic tables

  Agentic table processing now uses automatic mode by default. Automatic mode selects how much enrichment each table needs, keeping accuracy high while lowering latency. To keep full enrichment on every table, set the table mode to `max`. See [agentic table modes](/configs/parse/agentic-modes#table-mode) to learn more.

  #### New default models

  On June 21, 2026, new default models rolled out. The layout model updated to v3, with more accurate layout detection that parsing and downstream extraction rely on. The agentic table, text, and key-value models updated to v3 for better processing of tables, text, and key-value regions. Track current versions on the [model versions](/reference/model-versions) page, and pin a version with [version pinning](/reference/version-pinning) if you need stable output.

  #### Discounted batch processing

  Batch Queue is available for larger parse workloads that do not need immediate turnaround, such as backfills, data dumps, and overnight runs. Batch Queue processes these jobs at a lower cost. See [Batch Queue](/workflows/batch-queue) to learn more.

  #### Faster PDF rendering in Studio

  Studio's document display is now faster and smoother, which makes viewing long document corpuses easier.

  #### Retiring the legacy OCR option

  The legacy OCR option in the Parse API is being retired for all users. Starting Monday, June 22, 2026, requests that set the OCR system to `legacy` are served by the default OCR system instead. In the v3 config, `settings.ocr_system: legacy` is now served by `standard`. In the v2 config, `advanced_options.ocr_system: legacy` is now served by `highres`. These default OCR systems are faster than the legacy option.
</Update>

<Update
  label="May 2026"
  rss={{
title: "May 2026 - Deep Split, improved job execution, MCP server, and a redesigned Studio",
description: "May 2026 brings Deep Split for the Split endpoint, more reliable job execution, a native MCP server, and a redesigned Studio."
}}
>
  #### Deep Split

  [Deep Split](/configs/split/deep-split) brings an agent-based approach to the Split endpoint, improving segmentation on long documents.

  #### Improved job execution

  Job execution is more reliable, with lower latency on long documents and large jobs.

  #### Native MCP server

  A native Model Context Protocol (MCP) server lets agents call Reducto directly from tools like Claude and Cursor, using plain language to run document work on local files. See [the MCP server page](/mcp-server) to learn more.

  #### Redesigned Studio

  Studio has a refreshed look and feel, including light and dark modes.
</Update>

<Update
  label="April 2026"
  rss={{
title: "April 2026 - New extract model available for early access",
description: "April 2026 introduces a new extract model, available for early access via the alpha settings before it becomes the default."
}}
>
  #### New extract model

  A new extract model is available for early access before it becomes the default. It improves accuracy and recall, especially on long schemas and long-context documents. To try it, set the extract model to `v2` in your request settings. Citations must be enabled to use it:

  ```json theme={null}
  {
    "settings": {
      "citations": {
        "enabled": true
      },
      "alpha": {
        "extract_model": "v2"
      }
    }
  }
  ```

  Track current versions on the [model versions](/reference/model-versions) page, and pin a version with [version pinning](/reference/version-pinning) if you need stable output.
</Update>

<Update
  label="March 2026"
  rss={{
title: "March 2026 - Classify endpoint, Deep Extract, Smart Schema, and faster parsing",
description: "March 2026 introduces the Classify endpoint, Deep Extract for long and complex documents, Smart Schema for building extract schemas, and faster parsing."
}}
>
  #### Classify endpoint

  The new [Classify](/classify/overview) endpoint sorts documents into categories you define. Provide categories and criteria, and Classify assigns each document before you parse or extract.

  #### Deep Extract

  [Deep Extract](/configs/extract/deep-extract) is a new extraction option for long and complex documents. It uses a longer-running, self-verifying agent to improve accuracy on difficult extractions.

  #### Smart Schema

  Smart Schema helps you build and refine extract schemas. It suggests schema improvements and asks clarifying questions based on your document's context to improve results.

  #### Faster parsing

  Base parsing is now faster, so most non-agentic parse requests return more quickly. Spreadsheet parsing is also faster and more accurate.
</Update>