Skip to main content
Note: These credit rates apply to all subscriptions starting October 13th, 2025. Existing customers can reach out to support@reducto.ai for details based on their tier.

Parse Endpoint

Document and Image Formats

Supported formats include: Image Formats: PNG, JPEG/JPG, GIF, BMP, TIFF, PCX, PPM, APNG, PSD (Adobe Photoshop), CUR (Windows cursors), DCX (Fax applications), FTEX (3D textures), PIXAR raster files, HEIC (High Efficiency Image Codec) PDF: PDF (Portable Document Format) Presentations: PPTX (PowerPoint Open XML), PPT (PowerPoint Binary) Word Documents: DOCX (Word Open XML), DOC (Word Binary), DOTX (Word Template), WPD (WordPerfect)
Processing TypeCredits per PageDescription
Standard Page1Standard processing includes text, layout, simple tables, and formatting extraction—even for scanned pages that require OCR.
Complex Page2Complex pages that require VLM (Vision Language Model) enhancements. This includes complex tables, key-value regions, and images (when figure summarization is enabled). Reducto intelligently classifies complexity on a per-page basis for your documents.
Agentic Extraction - Standard Pages2When agentic extraction is enabled (agentic OCR, agentic tables, agentic figures), Reducto uses multiple passes of VLMs to optimize accuracy.
Agentic Extraction - Complex Pages4Agentic extraction applied to complex pages requires the highest level of processing.

Spreadsheet Formats

Supported formats include: CSV (Comma Separated Values), XLSX (Excel Open XML), XLSM (Excel with Macros), XLS (Excel Binary), XLTX (Excel Template), XLTM (Excel Macro-enabled Template), QPW (QuatroPro)
Clustering TypeCreditsDescription
Intelligent clustering1 credit per 500 cellsAdvanced clustering with intelligent grouping.
Standard clustering1 credit per 2,500 cellsBasic clustering functionality.

Text Formats

Supported formats include: HTML, TXT (Plain Text), RTF (Rich Text Format) Reducto returns a converted representation of the provided file.
Format TypeCredits per Page
Text formats0.5

Extract Endpoint

Processing TypeCredits per PageNotes
Default2Standard extraction processing.
Agent-In-Loop4Currently billed as default during beta access.
Note: If a parse ID is not provided, credit consumption for Extract requests will automatically add Parse credit consumption.

Split Endpoint

Processing TypeCredits per Page
Default2
Note: If a parse ID is not provided, credit consumption for Split requests will automatically add Parse credit consumption.

Edit Endpoint

The Edit endpoint is currently in beta with a temporary credit utilization rate that is subject to change.
Processing TypeCredits per PageNotes
Beta pricing4Temporary rate during beta.