[
  {
    "id": "reducto-docs-1",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/parse/overview",
    "excerpt": "Parse is Reducto’s foundational endpoint. It converts documents into structured JSON with text, tables, figures, layout, and formatting",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-2",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/extract/overview",
    "excerpt": "Extract pulls specific fields from documents as structured JSON. You define a schema describing the data you need, and Reducto returns values matching that schema",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-3",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/split",
    "excerpt": "Split identifies which pages contain which sections of a document. You describe sections in natural language, and Reducto returns the page numbers where each section lives.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-4",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai",
    "excerpt": "Route documents by type before processing. Define categories in natural language.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-5",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai",
    "excerpt": "Fill PDF forms and modify DOCX files programmatically with natural language instructions.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-6",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai",
    "excerpt": "Multi-step workflows that chain classification, parsing, extraction, and editing into single API calls",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-7",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/cli",
    "excerpt": "The Reducto CLI gives you direct terminal access to Reducto’s document capabilities: parse, extract, split, classify, and edit.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-8",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/mcp-server",
    "excerpt": "Once installed, agents in Claude Desktop, Claude Code, Codex, Cursor, VS Code, Windsurf, or any other Model Context Protocol client can classify, parse, extract, split, and edit documents",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-9",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/workflows/async-overview",
    "excerpt": "`run_job()` Calls async endpoint, returns job ID",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-10",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/workflows/svix-webhooks",
    "excerpt": "Svix webhooks provide cryptographic request signing, automatic retries with exponential backoff, and a delivery dashboard for debugging.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-11",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/extract/citations",
    "excerpt": "Citations tell you exactly where each extracted value came from in the document. When enabled, every field includes bounding box coordinates pointing to the source text.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-12",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/parse/chunking-methods",
    "excerpt": "Chunking lets you control this tradeoff without post-processing the response yourself.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-13",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/parse/agentic-modes",
    "excerpt": "Add an entry to the `agentic` array for each scope that needs customized processing. Each entry must include a custom prompt or enable advanced chart extraction.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-14",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/parse/table-output-formats",
    "excerpt": "Reducto extracts tables from documents and can return them in several formats.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-15",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/onprem/enterprise_deployment_options",
    "excerpt": "All data and storage reside in the customer’s VPC, while ephemeral processing is handled by Reducto’s dedicated GPU infrastructure.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-16",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/upload/overview",
    "excerpt": "Files over 100MB? Use the presigned URL method which supports files up to 5GB.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-17",
    "tier": "claimed-docs",
    "url": "https://reducto.ai/pricing",
    "excerpt": "If you're using another document processor, we'll give you up to $5,000 in credits to migrate your workload to Reducto.",
    "fetchedAt": "2026-09-10T18:45:32.380Z"
  },
  {
    "id": "reducto-docs-18",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/quickstart",
    "excerpt": "result = client.parse.run(input=\"https://cdn.reducto.ai/samples/fidelity-example.pdf\")",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-19",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/extract/overview",
    "excerpt": "You define a schema describing the data you need, and Reducto returns values matching that schema",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-20",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/split",
    "excerpt": "You describe sections in natural language, and Reducto returns the page numbers where each section lives.",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-21",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/parse/chunking-methods",
    "excerpt": "result = client.parse.run(\n    input=upload.file_id,\n    retrieval={\n        \"chunking\": {\n            \"chunk_mode\": \"variable\",\n            \"chunk_size\": 1000\n        }\n    }\n)",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-22",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/extract/citations",
    "excerpt": "When enabled, every field includes bounding box coordinates pointing to the source text.",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-23",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/workflows/async-overview",
    "excerpt": "`run_job()` | Calls async endpoint, returns job ID",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-24",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/mcp-server",
    "excerpt": "agents in Claude Desktop, Claude Code, Codex, Cursor, VS Code, Windsurf, or any other Model Context Protocol client can classify, parse, extract, split, and edit documents as part of their reasoning loop",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-25",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/reference/credit-usage",
    "excerpt": "Parse and Extract jobs submitted through the batch queue receive a 20% usage discount.",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-26",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/security/policies",
    "excerpt": "We have a Zero Data Retention policy (ZDR) for users on our “Growth” tier and above, meaning all data submitted via API is set to expire within 24 hours",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-27",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/enterprise/enterprise-readiness",
    "excerpt": "Enterprise customers receive contractual uptime SLAs of up to 99.99%.",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-docs-28",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/workflows/svix-webhooks",
    "excerpt": "In Reducto Studio, go to Webhooks in the sidebar. This opens your Svix dashboard directly.",
    "fetchedAt": "2026-09-10T18:48:49.798Z"
  },
  {
    "id": "reducto-supp-1",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/security/policies",
    "excerpt": "Security policies, data retention: \"We have a Zero Data Retention policy (ZDR) for users on our 'Growth' tier and above, meaning all data submitted via API is set to expire within 24 hours, except for Studio-run jobs and results saved with persist_results: true. This means that API-submitted data older than 24 hours is automatically deleted.\"",
    "fetchedAt": "2026-09-10T19:16:37.000Z"
  },
  {
    "id": "reducto-supp-2",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/security/policies",
    "excerpt": "Security policies, compliance: \"SOC 2 Type 2: We have completed our SOC 2 Type I and Type II process.\" and \"HIPAA Compliance: We currently offer a HIPAA compliant processing pipeline for Growth and Enterprise tier customers ... Please reach out to us via email to sign a BAA with us.\"",
    "fetchedAt": "2026-09-10T19:16:37.000Z"
  },
  {
    "id": "reducto-docs-29",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/parse/overview.md",
    "excerpt": "Parse is Reducto's foundational endpoint. It converts documents into structured JSON with text, tables, figures, layout, and formatting",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-30",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/classify/overview.md",
    "excerpt": "Classify determines what kind of document you are looking at before any downstream processing begins. You specify categories with natural language criteria, and Reducto returns the best match.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-31",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/cli.md",
    "excerpt": "The Reducto CLI gives you direct terminal access to Reducto's document capabilities: parse, extract, split, classify, and edit.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-32",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/mcp-server.md",
    "excerpt": "agents in Claude Desktop, Claude Code, Codex, Cursor, VS Code, Windsurf, or any other Model Context Protocol client can classify, parse, extract, split, and edit documents as part of their reasoning loop, without custom integration code.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-33",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/upload/large-files.md",
    "excerpt": "For files larger than 100MB, use the presigned URL method. This uploads directly to cloud storage, bypassing the 100MB limit of the standard Upload endpoint.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-34",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/studio-quickstart.md",
    "excerpt": "Build document workflows by configuring classification, parsing, extraction, and editing steps, test on real documents with the citation viewer, then deploy as a Pipeline ID callable from code.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-35",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/parse/best-practices.md",
    "excerpt": "Variable chunking splits at semantic boundaries like section headers, tables, and figures, keeping related content together while creating chunks sized for embedding models.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-36",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/workflows/async-overview",
    "excerpt": "client.parse.run_job() ... POST /parse_async ... Job ID (returns immediately)",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-37",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/parse/table-output-formats",
    "excerpt": "Reducto extracts tables from documents and can return them in several formats. The format you choose affects how merged cells, headers, and structure are represented.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-38",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/configs/parse/agentic-modes",
    "excerpt": "Use agentic processing with r-1 when your workflow needs a custom prompt for a specific content type or advanced chart extraction.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-39",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/workflows/svix-webhooks",
    "excerpt": "Svix webhooks provide cryptographic request signing, automatic retries with exponential backoff, and a delivery dashboard for debugging. Use Svix for production applications.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-docs-40",
    "tier": "claimed-docs",
    "url": "https://docs.reducto.ai/onprem/enterprise_deployment_options",
    "excerpt": "Customers can choose between a dedicated VPC deployment, a hybrid VPC model, and a fully hosted SaaS model, balancing control, cost, and compute performance.",
    "fetchedAt": "2026-09-16T21:52:39.295Z"
  },
  {
    "id": "reducto-comm-1",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44356799",
    "excerpt": "Congrats on the launch guys, mobile website seems to be broken though.",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-2",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44356799",
    "excerpt": "FYI - links.reducto.ai/studio doesn't seem to be working... ERR_TOO_MANY_REDIRECTS",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-3",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44356799",
    "excerpt": "Why do you only get a data processing agreement when on the enterprise plan? It's a legal requirement for any European company.",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-4",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44356799",
    "excerpt": "Mathpix founder: 'Reducto does cool stuff on post processing (and other input formats), but some people have told me Mathpix is better at just getting data out of PDFs accurately.'",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-5",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44356799",
    "excerpt": "Extend founder: 'the Reducto team seems to have cloned us down to the small details... We thought deeply about how to build an ergonomic configuration experience for recursive type definitions.'",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-6",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=44356799",
    "excerpt": "This would have saved me so much pain back when I was working on RAG workflows. Great to see.",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-7",
    "tier": "community",
    "url": "https://news.ycombinator.com/item?id=47662833",
    "excerpt": "We used Reducto and it did struggle with long documents. As we process financial documents going over 300+ pages using Gemini 3 Flash is producing high accuracy extracts super fast.",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-8",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/47662833",
    "excerpt": "Reducto founder: 'Deep Extract is more accurate than any structured extraction product we've tried, but the approach comes with a very clear cost/latency tradeoff over a single pass extraction.'",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-comm-9",
    "tier": "community",
    "url": "https://hn.algolia.com/api/v1/items/47204996",
    "excerpt": "Ask HN post: 'Looking for high-quality alternatives to Reducto for document parsing. Need strong table extraction + structured JSON output. Accuracy on messy PDFs is critical.'",
    "fetchedAt": "2026-09-10T18:50:17.448Z"
  },
  {
    "id": "reducto-probe-1",
    "tier": "probe",
    "url": "https://docs.reducto.ai/llms.txt",
    "excerpt": "PROBE llms.txt: HTTP 200 at https://docs.reducto.ai/llms.txt # Reducto\n\n- [Overview](https://docs.reducto.ai/overview.md): The agentic document platform for leading AI teams\n- [API",
    "fetchedAt": "2026-09-16T21:52:41.322Z"
  },
  {
    "id": "reducto-probe-2",
    "tier": "probe",
    "url": "https://docs.reducto.ai/openapi.json",
    "excerpt": "PROBE openapi: HTTP 200 at https://docs.reducto.ai/openapi.json — contains \"openapi\" key",
    "fetchedAt": "2026-09-16T21:52:41.322Z"
  },
  {
    "id": "reducto-probe-3",
    "tier": "probe",
    "url": "https://docs.reducto.ai/mcp-server",
    "excerpt": "official MCP server documented at https://docs.reducto.ai/mcp-server",
    "fetchedAt": "2026-09-16T21:52:41.322Z"
  },
  {
    "id": "reducto-probe-4",
    "tier": "probe",
    "url": "https://docs.reducto.ai/cli",
    "excerpt": "official CLI documented at https://docs.reducto.ai/cli",
    "fetchedAt": "2026-09-16T21:52:41.322Z"
  }
]