# Reducto API

## Docs

- [Reducto API Reference for Coding Agents](https://docs.reducto.ai/agent-guide.md): Complete, structured reference for AI coding agents integrating the Reducto document processing API
- [Parse Async](https://docs.reducto.ai/api-reference/async-parse.md)
- [Cancel Job](https://docs.reducto.ai/api-reference/cancel-job.md)
- [Edit](https://docs.reducto.ai/api-reference/edit.md)
- [Edit Async](https://docs.reducto.ai/api-reference/edit-async.md)
- [Extract](https://docs.reducto.ai/api-reference/extract.md)
- [Extract Async](https://docs.reducto.ai/api-reference/extract-async.md)
- [Get Jobs](https://docs.reducto.ai/api-reference/get-jobs.md)
- [Get Version](https://docs.reducto.ai/api-reference/get-version.md)
- [Parse](https://docs.reducto.ai/api-reference/parse.md)
- [Pipeline](https://docs.reducto.ai/api-reference/pipeline.md)
- [Pipeline Async](https://docs.reducto.ai/api-reference/pipeline-async.md)
- [Retrieve Job](https://docs.reducto.ai/api-reference/retrieve-parse.md)
- [Split](https://docs.reducto.ai/api-reference/split.md)
- [Split Async](https://docs.reducto.ai/api-reference/split-async.md)
- [Upload](https://docs.reducto.ai/api-reference/upload.md)
- [Webhook Portal](https://docs.reducto.ai/api-reference/webhook-portal.md)
- [Classify Best Practices](https://docs.reducto.ai/classify/best-practices.md): Write better classification schemas for more accurate results
- [Classify](https://docs.reducto.ai/classify/overview.md): Categorize documents before you parse
- [Classify Response Format](https://docs.reducto.ai/classify/response-format.md): Confidence scores, per-criterion reasoning, and all response fields
- [Reducto CLI](https://docs.reducto.ai/cli.md): Parse, extract, and edit documents from the command line.
- [SpreadsheetViewer](https://docs.reducto.ai/components/spreadsheet-viewer.md): A React component for viewing Excel spreadsheets with bounding box overlays for document extraction visualization
- [Classify Configuration](https://docs.reducto.ai/configs/classify/configuration.md): Configure page ranges and classification behavior
- [Form Schema](https://docs.reducto.ai/configs/edit/form-schema.md): Pre-define field locations for faster, more consistent PDF form filling
- [Array Extraction](https://docs.reducto.ai/configs/extract/array-extraction.md): Extract complete arrays from long documents without truncation
- [Citations](https://docs.reducto.ai/configs/extract/citations.md): Link extracted values to their source locations in the document
- [Deep Extract](https://docs.reducto.ai/configs/extract/deep-extract.md): Achieve near-perfect accuracy on complex and long extractions with our agentic loop
- [Configuration Overview](https://docs.reducto.ai/configs/overview.md): How Reducto's configuration system works
- [Additional Document Data](https://docs.reducto.ai/configs/parse/additional-document-data.md): Extract revision marks, comments, highlights, hyperlinks, and signatures
- [Agentic Modes](https://docs.reducto.ai/configs/parse/agentic-modes.md): AI-powered accuracy improvements for text, tables, and figures
- [Chart Extraction](https://docs.reducto.ai/configs/parse/chart-extraction.md): Extract structured data from charts and graphs
- [Chunking Methods](https://docs.reducto.ai/configs/parse/chunking-methods.md): Control how parsed content is grouped in API responses
- [Processing Settings](https://docs.reducto.ai/configs/parse/ocr-settings.md): Control OCR, timeouts, output options, and document handling
- [Page Ranges](https://docs.reducto.ai/configs/parse/page-ranges.md): Process specific pages of a document
- [Spreadsheet Processing](https://docs.reducto.ai/configs/parse/spreadsheet.md): Configure how Excel, CSV, and spreadsheet files are processed
- [Table Output Formats](https://docs.reducto.ai/configs/parse/table-output-formats.md): Control how tables are formatted in API responses
- [Split Configuration](https://docs.reducto.ai/configs/split/configuration.md): Configure how documents are divided into sections
- [Parallel Document Processing](https://docs.reducto.ai/cookbooks/batch-processing.md): Process hundreds of documents concurrently using AsyncReducto with progress tracking and error handling
- [Layout & Table Extraction to Analytics](https://docs.reducto.ai/cookbooks/financial-analysis.md): Extract and analyze financial data from 10-K annual reports using Parse, Extract, and table extraction
- [ACORD Insurance Forms](https://docs.reducto.ai/cookbooks/form-filling.md): Extract policy data from declarations pages and fill ACORD 25 certificates
- [ID & Onboarding Documents](https://docs.reducto.ai/cookbooks/identity-verification.md): Verify user identity by extracting and cross-matching data from ID cards, utility bills, and tax forms
- [Invoice & Accounts Payable Automation](https://docs.reducto.ai/cookbooks/invoice-extraction.md): Extract structured data from freight invoices using Reducto's Extract API with array extraction and citations
- [Multi-lingual Document Processing](https://docs.reducto.ai/cookbooks/multilingual-processing.md): Process documents in 60+ languages with automatic language detection and OCR configuration
- [Multimodal RAG with Image Results](https://docs.reducto.ai/cookbooks/multimodal-rag-image-results.md): Build a RAG system that retrieves and reasons over both text and images from documents
- [Cookbooks](https://docs.reducto.ai/cookbooks/overview.md): Step-by-step guides for common document processing tasks
- [Contract & Legal Document Review](https://docs.reducto.ai/cookbooks/redlined-legal-contracts.md): Parse redlined legal documents and extract insertions, deletions, and annotations as structured data
- [Web Browsing (Browserbase)](https://docs.reducto.ai/cookbooks/web-browsing-browserbase.md): Extract financial data from investor relations PDFs using Stagehand for AI-powered web browsing and Reducto for document processing
- [Edit](https://docs.reducto.ai/editing/edit-overview.md): Fill forms and modify documents with natural language instructions
- [Enterprise Readiness](https://docs.reducto.ai/enterprise/enterprise-readiness.md): How Reducto meets the security, reliability, and scale requirements of enterprise document processing
- [Extract](https://docs.reducto.ai/extract/overview.md): Pull specific data from documents into structured JSON
- [Extract Response Format](https://docs.reducto.ai/extract/response-format.md): Understanding extracted data, citations, and usage
- [Extract Best Practices](https://docs.reducto.ai/extraction/best-practices-extract.md): Schema design and prompt writing for reliable extractions
- [On-premise changelog](https://docs.reducto.ai/onprem/changelog.md): Release notes for on-premise deployments of Reducto
- [Deployment options (Cloud, On-prem, Hybrid)](https://docs.reducto.ai/onprem/enterprise_deployment_options.md): Flexible, secure deployment options designed to meet enterprise data-governance, performance, and scalability requirements
- [Self-hosted fair queueing with Reducto](https://docs.reducto.ai/onprem/fair_queueing.md): Fair queueing by user-id for on-premise deployment
- [Automatic file cleanup](https://docs.reducto.ai/onprem/file_cleanup.md): Configure automatic deletion of uploaded files in Reducto
- [Hybrid VPC — AWS S3](https://docs.reducto.ai/onprem/hybrid-vpc-aws.md): Set up Hybrid VPC with AWS S3 storage and optional PrivateLink
- [Hybrid VPC — Azure Blob Storage](https://docs.reducto.ai/onprem/hybrid-vpc-azure.md): Set up Hybrid VPC with Azure Blob Storage for data sovereignty
- [Hybrid VPC — Box](https://docs.reducto.ai/onprem/hybrid-vpc-box.md): Set up Hybrid VPC with Box as your document storage backend
- [Hybrid VPC Deployment](https://docs.reducto.ai/onprem/hybrid-vpc-deployment.md): Deploy Reducto with your data in your own cloud account and compute managed by Reducto
- [Hybrid VPC — Google Cloud Storage](https://docs.reducto.ai/onprem/hybrid-vpc-gcs.md): Set up Hybrid VPC with Google Cloud Storage for data sovereignty
- [LLM & service configuration options](https://docs.reducto.ai/onprem/llm_options.md): Complete guide to LLM configuration and environment variables for Reducto
- [Observability & Monitoring](https://docs.reducto.ai/onprem/observability.md): Built-in observability stack for on-premise Reducto deployments
- [Securing Reducto](https://docs.reducto.ai/onprem/securing_reducto.md): Learn how to secure on-premise Reducto deployments
- [Air-gapped usage for billing](https://docs.reducto.ai/onprem/usage_for_billing.md): Export usage data from air-gapped environments for billing purposes
- [Overview - What is Reducto?](https://docs.reducto.ai/overview.md): Transform unstructured documents into structured data
- [Parse Best Practices](https://docs.reducto.ai/parse/best-practices.md): Key practices for getting the best results from Parse
- [Parse](https://docs.reducto.ai/parse/overview.md): Convert documents into structured JSON with text, tables, and figures
- [Parse Response Format](https://docs.reducto.ai/parse/response-format.md): Understanding chunks, blocks, and bounding boxes
- [API Quickstart](https://docs.reducto.ai/quickstart.md): Extract text, tables, and figures from documents using the Reducto API.
- [Credit Usage](https://docs.reducto.ai/reference/credit-usage.md): Understanding how credits are calculated across Reducto endpoints
- [Error Codes](https://docs.reducto.ai/reference/error-codes.md): Understanding and handling Reducto API errors
- [Frequently Asked Questions](https://docs.reducto.ai/reference/faq.md): Common questions about using Reducto
- [Glossary](https://docs.reducto.ai/reference/glossary.md): Key terms and concepts in Reducto
- [Per-Page Billing Breakdown](https://docs.reducto.ai/reference/page-billing-breakdown.md): Understand exactly which billing features were applied to each page of your document
- [Rate Limits](https://docs.reducto.ai/reference/rate-limits.md): API request limits and optimization strategies
- [Version Pinning](https://docs.reducto.ai/reference/version-pinning.md): How Reducto model versioning works and how to pin versions
- [EU data residency & processing](https://docs.reducto.ai/security/eu-data-residency.md): For customers requiring that all document data stays strictly within EU
- [Filing Complaints](https://docs.reducto.ai/security/filing-complaints.md)
- [Data policies & compliance](https://docs.reducto.ai/security/policies.md)
- [Split](https://docs.reducto.ai/split.md): Divide documents into logical sections for targeted processing
- [Account & Settings](https://docs.reducto.ai/studio-account.md): Manage API keys, usage, billing, and organization settings in Reducto Studio
- [Deploying to Production](https://docs.reducto.ai/studio-deploy-pipeline.md): Publish pipelines, integrate with API, and monitor production usage
- [Edit Pipeline](https://docs.reducto.ai/studio-edit.md): Fill forms and modify documents with natural language instructions in Reducto Studio
- [Extract Pipeline](https://docs.reducto.ai/studio-extract.md): Pull specific fields from documents as structured JSON in Reducto Studio
- [Parse Pipeline](https://docs.reducto.ai/studio-parse.md): Turn documents into structured data in Studio
- [Studio Quickstart](https://docs.reducto.ai/studio-quickstart.md): Extract from your first document in Reducto Studio and deploy it to production.
- [Split Pipeline](https://docs.reducto.ai/studio-split.md): Divide documents into sections for targeted workflows in Studio
- [Uploading Large Files](https://docs.reducto.ai/upload/large-files.md): Upload files up to 5GB using presigned URLs
- [Upload](https://docs.reducto.ai/upload/overview.md): Upload documents to Reducto for processing
- [Async Processing](https://docs.reducto.ai/workflows/async-overview.md): Process documents asynchronously with job queues, polling, and webhooks
- [Batch Processing](https://docs.reducto.ai/workflows/batch-processing.md): Process multiple documents in parallel
- [Chaining API Calls](https://docs.reducto.ai/workflows/chaining-endpoints.md): Combine Classify, Parse, and Extract to build document processing workflows
- [Direct Webhooks](https://docs.reducto.ai/workflows/direct-webhooks.md): Simple HTTP POST webhooks for prototyping and basic integrations
- [Multi-document Pipelines](https://docs.reducto.ai/workflows/multi-document-pipelines.md): Process related documents together with shared context for extraction
- [Pipeline Basics](https://docs.reducto.ai/workflows/pipeline-basics.md): Combine Reducto's capabilities into reusable, single-call workflows
- [Svix Webhooks](https://docs.reducto.ai/workflows/svix-webhooks.md): Enterprise-grade webhook delivery with signing, retries, and dashboard

## OpenAPI Specs

- [openapi](https://docs.reducto.ai/openapi.json)
- [openapi-legacy](https://docs.reducto.ai/openapi-legacy.json)

## Optional

- [Status](https://status.reducto.ai)
- [Studio](https://studio.reducto.ai)
- [Support](mailto:support@reducto.ai)