Changelog

Advanced Excel parsing can now preserve source-cell provenance and formatting in parse output.

• Set advancedOptions.excelIncludeCellMetadata to return source cell references such as B2 or merged ranges such as A1:C1; formula cells also include the source formula text.
• Set advancedOptions.excelIncludeCellFormatting to return structured cell formatting such as bold, italic, font color, and background color.
• For HTML table output, metadata is also emitted as data-cell and data-formula attributes, and formatting preserves inline cell styles.

You can now provide custom instructions for figure parsing via blockOptions.figures.customInstructions. The instructions (up to 2,000 characters) are injected into the vision model prompt that analyzes and summarizes each figure, letting you steer descriptions toward your use case — for example, domain-specific terminology or details to always capture from diagrams.

Run responses now include a finer-grained credit breakdown. Each entry in usage.breakdown can now include a charges array that itemizes the cost drivers behind that run’s credits — for example base processor, review agent, or page-specific add-ons like agentic text correction. Each charge lists the billing product, unit (page or cell), quantity, credits consumed, and applicable page numbers when billing is page-scoped.

You can now cancel parse runs that are still processing. Call POST /parse_runs/{id}/cancel on the 2026-02-09 API to cancel an in-progress parse run and set its status to CANCELLED. Only runs with status PROCESSING can be cancelled.

• POST /parse_runs/{id}/cancel — abort an in-progress parse run (2026-02-09 API)

Workflow validation formulas now support INCLUDES and INCLUDESANY for checking whether text appears inside any element of an array field. Unlike CONTAINS and CONTAINSALL, which match whole array elements, these operators perform case-insensitive substring checks—useful when you need to verify that one or more keywords appear in fields such as line item descriptions.

Parse runs now include minOcrConfidence and avgOcrConfidence on chunk and block metadata — the minimum and average per-word OCR confidence across the words in that region.

Both fields are returned on every chunk and block, and are null when word-level confidence isn’t produced for that region. Values are in the range 0–1.

For API version 2026-02-09, you can optionally pass generate on POST /extractors instead of supplying config. Provide one to five sample inputs as Extend file IDs or file URLs and Extend will generate a JSON extraction schema from those examples and return the extractor with the schema applied. Optionally add generate.instructions (up to 2,500 characters) to provide additional context about the document type or requirements for how values should be extracted. You cannot combine generate with cloneExtractorId or config.

Extraction Performance 4.8.0 is now the latest base processor version. It upgrades the base models used for core extraction and large array strategies

You can opt in to an advanced extraction setting that adds a fixed “current date” line to the system prompt. The model can use it when a field depends on today, relative phrases like “30 days from now”, or ambiguous short dates on the page (for example interpreting 02/03/26). The value is taken from when the run was created in UTC.

The option is off by default. For API version 2026-02-09, set advancedOptions.currentDateEnabled to true. See the JSON Schema extraction guide for how advanced options fit into your setup.

Run objects now include richer usage metadata so you can see how credits relate to underlying work alongside the billed amount (credits). The existing usage.credits value is unchanged. For full run payloads and webhook events, responses can also include totalCredits, representing all contributing charges for that logical run (for example extraction plus parsing when parsing was billed for that run), and a breakdown array listing each contributing resource type, id, and credit amount.

When bounding box citations are enabled on an extractor, you can set citationMode in advancedOptions to line, word, or block so citation polygons match the granularity you want. If you leave it unset, behavior matches what you have today (line-based citation processing plus block overlap handling across supported parse engines).

Extraction pipelines that use the parse 2.0.0-beta engine can now return bounding box citations for extracted values, so you are not limited to older parse versions when you need spatial references.

Two new endpoints make bulk background processing easier:

• /extract/batch — queue thousands of files for extraction in the background without running into rate limits.
• /parse/batch — bulk background parse operations.

Composer is now available for splitters, so you can optimize them automatically from eval sets. Previously, Composer was only available for extractors and classifiers.

If you’re working on splitting, check out our Splitter Benchmark to see how we evaluate models.

The new parse engine can now parse formula blocks as LaTeX. Enable it as an advanced option to extract math content directly from documents.

The new parse engine now detects and annotates strikethrough text via a specialized model. Enable it as an advanced option in the parser config.

You can now create, update, and delete workflows and workflow versions entirely via API. Previously, workflows could only be managed in the Extend dashboard. This makes it easier to generate workflows programmatically, check configs into code, manage them with CI/CD, and build them with agents like Claude Code.

1
await client.workflows.update("workflow_abc123", {
2
    steps: [
3
      { "name": "trigger", "type": "TRIGGER", "next": [{ "step": "parse" }] },
4
      { "name": "parse", "type": "PARSE", "next": [{ "step": "split" }] },
5
      {
6
        "name": "split",

The form detection and schema generation we offer in Studio is now available as a standalone API, making it faster to create forms and templates for known document types.

See the API reference.

The Light Parser now uses our new layout model, with smaller models for tables, forms, reading order, and other layout types — at a fraction of the cost and latency of the Performance Parser. It’s built for very high-volume ingestion workloads where cost matters, billed at 0.5 credits per page.

You can now include signature images in your e-signing workflows for more complete digital signing experiences.

See the API reference.

A new compare UI in the parse playground lets you quickly see differences between parse engines and advanced options side by side.