{
  "openapi": "3.1.0",
  "x-zeroclick-navigation": {
    "fullSpec": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json",
    "services": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services",
    "serviceSpecTemplate": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/{slug}/openapi.json",
    "searchTemplate": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json?q={text}",
    "operationTemplate": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json?path={path}&method={method}",
    "firstPage": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json?page=1",
    "instructions": [
      "Use this spec if it contains the operation and details you need. Otherwise, search or open a relevant service spec using the links below.",
      "Find service slugs in x-zeroclick-services or x-payment-info.rates[].service; use them in serviceSpecTemplate, never as request values.",
      "URL-encode template values. Search is ranked; service, path, and method filters are exact. Filters combine.",
      "Pages contain up to 10 operations; follow info.x-next or the Link header if you need more results. Shared operations retain all selector values."
    ]
  },
  "info": {
    "title": "Unsiloed AI",
    "version": "1.0.0",
    "description": "Unsiloed AI turns PDFs, Word documents, scans, images, slide decks and spreadsheets into structured output for language models and agents. Other formats are converted to PDF before submission. Parse returns a document as ordered Markdown and HTML chunks with segment types, bounding boxes, OCR text and confidence scores. Extract pulls the fields named in a JSON Schema out of a PDF, with a confidence score and a page citation on every value. Classify assigns a PDF or image to one of the categories supplied with the request, with a confidence score per page. Split cuts a bundled PDF into one file per category. Every operation is a job: the submit call returns a job id at once and the result call returns the output when the job finishes, usually within seconds to a few minutes. Documents are sent by URL. Usage is counted in pages of the submitted document: one PDF page, one image, one slide, or one block of 5,000 by 5,000 spreadsheet cells is one page. This server is a pay-per-use, transparent proxy in front of Unsiloed AI's own API: it handles identity, payment, and proxying. Agents can purchase autonomously or with their human's approval. The complete verified paid surface is listed at /openapi.json, the source of truth for available operations. Each operation here carries its live price in x-payment-info. Use the operations and details here when they meet your needs. Filtered specs contain only matching operations; if you cannot find what you need here, use search or the service catalog. The live catalog at /manifest.json is authoritative for prices and any free included units (prices[].includedUnits) - some meters include free usage per account before any charge, reserved for agents claimed by a human with a verified email.",
    "contact": {
      "email": "support@unsiloed.ai"
    },
    "x-guidance": "Start with the free seller advisor: POST https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/zeroclick/agent/quote with your goal and known budget or requirements. This operation costs $0 and requires only an x402 or MPP wallet proof; it returns a guide and never executes a purchase. Without a wallet, GET https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/zeroclick/agent/guide?goal=URL_ENCODED_TASK or POST to that guide. Other operations below are the direct API reference; their own prices and access requirements still apply. Call the operations listed in this document at https://agents.unsiloed.ai. Each service's full price matrix, plans, and how to buy are at https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/{slug}; each operation's x-payment-info names the service it bills by slug (rates[].service). Slugs identify services in prices and usage reports and are never request values: when one operation serves several services, its request body schema lists the accepted values of the field that selects the service, so send one of those exactly as written. An unpaid call returns 402 Payment Required with a signed challenge; settle it with a supported payment method - x402 (Base USDC) or MPP (Tempo USDC) today - and retry with the proof attached. No upstream API key is needed, and an agent without a payment method can set one up instantly at no cost. Read GET https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/manifest.json for the live services, meters, plans, prices, and any free included units, and https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/llms-full.txt for the full agent guide, including how the free allowance works without funding (it requires an agent identity claimed by a human with a verified email). Every call also needs your agent credential: register once (recipe at https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/auth.md) and send Authorization: Bearer <token>, or ZC-Agent-Authorization: Bearer <token> alongside an MPP Payment credential; a call without it answers 401 bearer_required before any price is quoted."
  },
  "x-service-info": {
    "categories": [
      "ai"
    ],
    "docs": {
      "homepage": "https://www.unsiloed.ai",
      "apiReference": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json",
      "llms": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/llms.txt"
    }
  },
  "externalDocs": {
    "url": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/llms-full.txt",
    "description": "How to authenticate, pay, and call this API; links the upstream API reference."
  },
  "servers": [
    {
      "url": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn",
      "description": "Pay-per-use access to Unsiloed AI's API"
    }
  ],
  "security": [
    {
      "payPerUse": [],
      "agentBearer": []
    }
  ],
  "components": {
    "securitySchemes": {
      "payPerUse": {
        "type": "apiKey",
        "in": "header",
        "name": "x-payment",
        "description": "Pay-per-use access. An unpaid call returns 402 Payment Required with a signed challenge; settle it with a supported payment method (x402 or MPP today) and retry with the proof in this header (x402) or as Authorization: Payment (MPP; use ZC-Agent-Authorization for a separate buyer bearer). No upstream API key is needed, and an agent without a payment method can set one up instantly at no cost."
      },
      "agentBearer": {
        "type": "http",
        "scheme": "bearer",
        "description": "Agent identity credential, required on every call: register once (anonymous registration is one free API call; the recipe is at https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/auth.md), exchange the assertion for an access token, and send Authorization: Bearer <token> - or ZC-Agent-Authorization: Bearer <token> when Authorization carries an MPP Payment credential. A call without it answers 401 bearer_required before any price is quoted."
      },
      "sellerAgentX402": {
        "type": "apiKey",
        "in": "header",
        "name": "Payment-Signature",
        "description": "Signed $0 x402 proof from the 402 challenge"
      },
      "sellerAgentMpp": {
        "type": "http",
        "scheme": "Payment",
        "description": "Signed $0 MPP proof from the 402 challenge"
      }
    },
    "schemas": {
      "sds_NhuZy9GOUeiFES-p8ND-N_c8cef78e290bd936_ref0": {
        "type": "object",
        "required": [
          "file"
        ],
        "properties": {
          "url": {
            "type": [
              "string",
              "null"
            ],
            "description": "Presigned or public URL of the document to fetch and process.\nRequired if `file` is not provided."
          },
          "file": {
            "type": "string",
            "format": "binary",
            "description": "Document file to process. Required if `url` is not provided.\nSupported formats: PDF, PNG, JPEG, TIFF, WebP, PPT, PPTX, DOC, DOCX, XLS, XLSX, HTML, HTM."
          },
          "mode": {
            "enum": [
              "fast",
              "agentic_lite",
              "agentic"
            ],
            "type": "string",
            "nullable": true,
            "description": "Processing mode preset. `fast` (Fast), `agentic_lite` (Agentic Lite), or `agentic` (Agentic). Each mode applies a recommended processing configuration; see [Processing Modes](/document-processing/parsing/processing-modes). Parameters you send explicitly take precedence over the mode. Omit to use the default configuration."
          },
          "detect_pii": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Run a PII pre-check before parsing. When enabled, the document is scanned\nfor personally identifiable information before any extraction work happens.\nIf PII is found, the task is rejected and\nno parsing occurs (the job ends in a failed state with a PII reason).\nDefaults to `false`."
          },
          "expires_in": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int32",
            "description": "Reserved field. Persisted in the task configuration but currently has no\neffect on retention for this endpoint — `POST /parse` (multipart and JSON/Form)\ndoes not set the task's `expires_at` column, and the cleanup job only deletes\n`AwaitingUpload` rows past their `expires_at`. To get a presigned-upload TTL,\nuse `POST /v2/parse/upload` instead, where `expires_in` controls the upload\nURL's validity."
          },
          "page_range": {
            "type": [
              "string",
              "null"
            ],
            "description": "Page range to process. Formats: `\"1-5\"`, `\"2,4,6\"`, `\"[1,3,5]\"`. Defaults to all pages."
          },
          "merge_tables": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Merge tables that span multiple pages into a single unified structure. Defaults to `false`."
          },
          "xml_citation": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Extract and hyperlink bibliography citations in the markdown output. PDFs only.\nDefaults to `false`."
          },
          "export_format": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_c8cef78e290bd936_ref1"
            },
            "example": [
              "docx",
              "markdown",
              "json"
            ],
            "description": "Export format(s) to generate after processing.\nWhen set, the pipeline generates the requested export files after parsing completes.\nThe exported files are available as presigned URLs in the `exports` field of the response.\nSupported: `[\"docx\", \"markdown\", \"json\"]`."
          },
          "extract_links": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Attach hyperlink URLs from PDF annotations to OCR results. Defaults to `false`."
          },
          "output_fields": {
            "type": [
              "string",
              "null"
            ],
            "description": "JSON object filtering which fields appear on each segment / chunk.\nEach key defaults to `true`; set a key to `false` to drop the field.\nKeys: `bbox`, `chart_data`, `confidence`, `content`, `embed`, `html`,\n`image`, `markdown`, `ocr`. Example: `{\"html\": false, \"ocr\": false}`."
          },
          "error_handling": {
            "type": [
              "string",
              "null"
            ],
            "default": "Continue",
            "description": "Error handling strategy for non-critical processing errors.\n`Continue` (default) — proceed despite errors (e.g., LLM refusals).\n`Fail` — stop and fail the task on any error."
          },
          "extract_charts": {
            "enum": [
              "basic",
              "standard",
              "advanced"
            ],
            "type": "string",
            "default": "basic",
            "nullable": true,
            "description": "Digitize charts into the numbers they were drawn from, attached to the Picture segment as `chart_data`. `basic` (default): no chart data. `standard`: fast and accurate chart data extraction. `advanced`: for the most complex and messiest charts; contact support to have it enabled for your organization (otherwise `403` with `error.code` = `feature_not_enabled`)."
          },
          "extract_colors": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Transfer text color from the PDF text layer to OCR results. Defaults to `false`."
          },
          "segment_filter": {
            "type": [
              "string",
              "null"
            ],
            "default": "all",
            "description": "Content filter: comma-separated segment types to keep.\nExample: `\"table,picture\"`. Use `\"all\"` to include everything. Defaults to `\"all\"`."
          },
          "segment_analysis": {
            "type": [
              "string",
              "null"
            ],
            "description": "JSON object controlling HTML/Markdown generation and custom VLM prompts per segment type.\nExample: `{\"Table\": {\"html\": \"VLM\", \"vlm\": \"Preserve merged cells.\"}}`."
          },
          "validate_segments": {
            "type": [
              "string",
              "null"
            ],
            "description": "JSON array string of segment types to validate with VLM.\nExample: `[\"Table\", \"Formula\", \"Picture\"]`. Defaults to `[]`."
          },
          "enhance_reading_order": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Reorder detected segments to follow the document's natural reading order.\nUseful for multi-column layouts (newspapers, two- or three-column papers).\nDefaults to `false`."
          },
          "extract_strikethrough": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Preserve strikethrough formatting in HTML/Markdown output. Defaults to `false`."
          }
        },
        "description": "Request body for `POST /parse` (multipart/form-data).\n\nProvide either `file` (binary upload) or `url` (presigned/public URL) — not both."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_c8cef78e290bd936_ref1": {
        "enum": [
          "docx",
          "markdown",
          "json"
        ],
        "type": "string",
        "description": "File format for exporting parsed results. When specified in a parse request,\nthe pipeline generates the requested export file after processing completes.\nThe exported file is available via the `exports` field in the task response."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_c8cef78e290bd936_ref2": {
        "type": "object",
        "required": [
          "job_id",
          "status",
          "file_name",
          "created_at",
          "message",
          "credit_used",
          "quota_remaining",
          "merge_tables"
        ],
        "properties": {
          "job_id": {
            "type": "string",
            "description": "Job identifier — pass this to `GET /parse/{job_id}` to poll for results."
          },
          "status": {
            "type": "string",
            "description": "Initial job status. Always `\"Starting\"` on creation."
          },
          "message": {
            "type": "string",
            "description": "Human-readable status message with a polling hint."
          },
          "file_name": {
            "type": "string",
            "description": "Name of the uploaded file or `\"unknown\"` when a URL was provided."
          },
          "created_at": {
            "type": "string",
            "description": "ISO 8601 timestamp when the job was created."
          },
          "credit_used": {
            "type": "integer",
            "format": "int32",
            "description": "Number of pages deducted from your quota for this job."
          },
          "merge_tables": {
            "type": "boolean",
            "description": "Whether table merging is enabled for this job (reflects the submitted `merge_tables` value)."
          },
          "quota_remaining": {
            "type": "integer",
            "format": "int64",
            "description": "Remaining page quota after this job was deducted."
          }
        },
        "description": "Response body for a successful `POST /parse` call."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_fd7fdafe238897e0_ref0": {
        "type": "object",
        "required": [
          "file"
        ],
        "properties": {
          "url": {
            "type": [
              "string",
              "null"
            ],
            "description": "Presigned or public URL of the workbook to fetch. Required if `file` is not provided."
          },
          "file": {
            "type": "string",
            "format": "binary",
            "description": "Excel workbook to process. Required if `url` is not provided. Supported: XLS, XLSX."
          },
          "expires_in": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int32",
            "description": "Reserved field. Persisted in the task configuration but currently has no\neffect on retention — Excel tasks use the same `Task::new_fast` creation\npath as `POST /parse`, which does not set the task's `expires_at` column.\nSee the same note on `ParseCreateRequest.expires_in`."
          },
          "exclude_hidden": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "Drop hidden sheets/rows/cols/styling from the output. Defaults to `false`."
          },
          "exclude_images": {
            "type": [
              "boolean",
              "null"
            ],
            "default": false,
            "description": "When excluding hidden content, also drop embedded/pasted images. Defaults to `false`."
          },
          "exclude_styling": {
            "type": [
              "boolean",
              "null"
            ],
            "default": true,
            "description": "When excluding hidden content, also drop styling. Defaults to `true`."
          },
          "split_large_tables": {
            "type": [
              "boolean",
              "null"
            ],
            "default": true,
            "description": "Split large tables into smaller segments. Defaults to `true`."
          },
          "exclude_hidden_cols": {
            "type": [
              "boolean",
              "null"
            ],
            "default": true,
            "description": "When excluding hidden content, also drop hidden columns. Defaults to `true`."
          },
          "exclude_hidden_rows": {
            "type": [
              "boolean",
              "null"
            ],
            "default": true,
            "description": "When excluding hidden content, also drop hidden rows. Defaults to `true`."
          },
          "max_rows_per_segment": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int32",
            "default": 50,
            "description": "Max rows per split segment when `split_large_tables`. Defaults to `50`."
          },
          "exclude_hidden_sheets": {
            "type": [
              "boolean",
              "null"
            ],
            "default": true,
            "description": "When excluding hidden content, also drop hidden sheets. Defaults to `true`."
          }
        },
        "description": "Request body for `POST /parse/excel` (multipart/form-data).\n\nExcel parsing has its own configuration — none of the PDF parsing options\n(OCR, layout analysis, segment processing) apply. Provide either `file`\n(binary .xls/.xlsx upload) or `url`, not both. Every config field is optional\nand defaults to the Excel pipeline's own default."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_fd7fdafe238897e0_ref1": {
        "type": "object",
        "required": [
          "job_id",
          "status",
          "file_name",
          "created_at",
          "message",
          "credit_used",
          "quota_remaining",
          "merge_tables"
        ],
        "properties": {
          "job_id": {
            "type": "string",
            "description": "Job identifier — pass this to `GET /parse/{job_id}` to poll for results."
          },
          "status": {
            "type": "string",
            "description": "Initial job status. Always `\"Starting\"` on creation."
          },
          "message": {
            "type": "string",
            "description": "Human-readable status message with a polling hint."
          },
          "file_name": {
            "type": "string",
            "description": "Name of the uploaded file or `\"unknown\"` when a URL was provided."
          },
          "created_at": {
            "type": "string",
            "description": "ISO 8601 timestamp when the job was created."
          },
          "credit_used": {
            "type": "integer",
            "format": "int32",
            "description": "Number of pages deducted from your quota for this job."
          },
          "merge_tables": {
            "type": "boolean",
            "description": "Whether table merging is enabled for this job (reflects the submitted `merge_tables` value)."
          },
          "quota_remaining": {
            "type": "integer",
            "format": "int64",
            "description": "Remaining page quota after this job was deducted."
          }
        },
        "description": "Response body for a successful `POST /parse` call."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref0": {
        "type": "object",
        "required": [
          "job_id",
          "status",
          "created_at",
          "metadata"
        ],
        "properties": {
          "chunks": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref1"
            },
            "description": "Array of document chunks with segments and extracted content. Present when status is `Succeeded`."
          },
          "job_id": {
            "type": "string",
            "description": "Job identifier."
          },
          "status": {
            "type": "string",
            "description": "Current job status: `Starting`, `Processing`, `Succeeded`, `Failed`, or `Cancelled`."
          },
          "exports": {
            "type": [
              "object",
              "null"
            ],
            "description": "Presigned download URLs for exported file formats.\nOnly present when `export_format` was specified in the parse request and the export has completed.\nKeys are format names (e.g. `\"docx\"`), values are presigned S3 URLs valid for 1 hour.\nExample: `{\"docx\": \"https://s3.amazonaws.com/...\"}`.\nIf export failed, contains `{\"docx_error\": \"...\"}` instead.",
            "propertyNames": {
              "type": "string"
            },
            "additionalProperties": {
              "type": "string"
            }
          },
          "message": {
            "type": [
              "string",
              "null"
            ],
            "description": "Error or status detail message. Present when status is `Failed`."
          },
          "pdf_url": {
            "type": [
              "string",
              "null"
            ],
            "description": "Presigned S3 URL to the generated PDF. Present when status is `Succeeded`."
          },
          "file_url": {
            "type": [
              "string",
              "null"
            ],
            "description": "S3 URL of the original uploaded file."
          },
          "metadata": {
            "type": "object",
            "description": "Citation or job metadata. Populated when `xml_citation` is enabled or from the job record."
          },
          "file_name": {
            "type": [
              "string",
              "null"
            ],
            "description": "Original file name from the job record."
          },
          "file_type": {
            "type": [
              "string",
              "null"
            ],
            "description": "MIME type of the uploaded file."
          },
          "created_at": {
            "type": "string",
            "description": "ISO 8601 timestamp when the job was created."
          },
          "page_count": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int64",
            "description": "Number of pages in the document. Present when status is `Succeeded`."
          },
          "started_at": {
            "type": [
              "string",
              "null"
            ],
            "description": "ISO 8601 timestamp when processing started. Present when status is not `Starting`."
          },
          "credit_used": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int64",
            "description": "Credits used for this job."
          },
          "finished_at": {
            "type": [
              "string",
              "null"
            ],
            "description": "ISO 8601 timestamp when processing completed. Present when status is `Succeeded` or `Failed`."
          },
          "total_chunks": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int64",
            "description": "Total number of document chunks. Present when status is `Succeeded`."
          },
          "configuration": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref8",
                "description": "Configuration used for this job (mirrors the parameters submitted at creation time).\nThe effective `merge_tables` value lives at `configuration.merge_tables`."
              }
            ]
          }
        },
        "description": "Response body for `GET /parse/{job_id}`.\n\nFields marked as optional appear only when the job has reached the relevant status."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref1": {
        "type": "object",
        "required": [
          "chunk_length",
          "segments"
        ],
        "properties": {
          "embed": {
            "type": [
              "string",
              "null"
            ],
            "description": "Suggested text to be embedded for the chunk. This text is generated by combining the embed content\nfrom each segment according to the configured embed sources (HTML, Markdown, LLM, or Content)."
          },
          "chunk_id": {
            "type": "string",
            "description": "The unique identifier for the chunk."
          },
          "segments": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref2"
            },
            "description": "Collection of document segments that form this chunk.\nWhen `target_chunk_length` > 0, contains the maximum number of segments\nthat fit within that length (segments remain intact).\nOtherwise, contains exactly one segment."
          },
          "chunk_length": {
            "type": "integer",
            "format": "int32",
            "minimum": 0,
            "description": "The total number of tokens in the chunk. Calculated by the `tokenizer`."
          }
        }
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref2": {
        "type": "object",
        "required": [
          "content",
          "html",
          "markdown",
          "page_height",
          "page_width",
          "page_number",
          "segment_id",
          "segment_type"
        ],
        "properties": {
          "ocr": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref5"
            },
            "description": "OCR results for the segment."
          },
          "bbox": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref3"
              }
            ]
          },
          "html": {
            "type": "string",
            "description": "HTML representation of the segment."
          },
          "image": {
            "type": [
              "string",
              "null"
            ],
            "description": "Presigned URL to the image of the segment."
          },
          "content": {
            "type": "string",
            "description": "Text content of the segment. By default, this contains OCR-extracted text."
          },
          "markdown": {
            "type": "string",
            "description": "Markdown representation of the segment."
          },
          "chart_data": {
            "description": "Extracted chart data for Picture segments identified as charts.\nContains structured data including chart_type, data series, labels, and legend."
          },
          "confidence": {
            "type": [
              "number",
              "null"
            ],
            "format": "float",
            "description": "Confidence score of the layout analysis model"
          },
          "page_width": {
            "type": "number",
            "format": "float",
            "description": "Width of the page containing the segment."
          },
          "references": {
            "type": [
              "array",
              "null"
            ],
            "items": {},
            "description": "GROBID research-paper citations attached to this segment."
          },
          "segment_id": {
            "type": "string",
            "description": "Unique identifier for the segment."
          },
          "page_height": {
            "type": "number",
            "format": "float",
            "description": "Height of the page containing the segment."
          },
          "page_number": {
            "type": "integer",
            "format": "int32",
            "minimum": 0,
            "description": "Page number of the segment."
          },
          "segment_type": {
            "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref7"
          },
          "cell_references": {
            "type": [
              "array",
              "null"
            ],
            "items": {},
            "description": "Spreadsheet cell-range references ({ sheet, address, ref }) for Excel\nsegments. Distinct from `references` (GROBID citations) so the two\nconcepts never collide in the output or on the frontend."
          },
          "merged_page_bboxes": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref4"
            },
            "description": "Per-page bbox info for all pages of a merged multi-page table.\nOnly present on merged table segments (segment_id ends with \"_merged\")."
          },
          "segment_type_display": {
            "type": [
              "string",
              "null"
            ],
            "description": "Display name for the segment type (used for serialization based on naming convention)"
          }
        }
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref3": {
        "type": "object",
        "required": [
          "left",
          "top",
          "width",
          "height"
        ],
        "properties": {
          "top": {
            "type": "number",
            "format": "float",
            "description": "The top coordinate of the bounding box."
          },
          "left": {
            "type": "number",
            "format": "float",
            "description": "The left coordinate of the bounding box."
          },
          "width": {
            "type": "number",
            "format": "float",
            "description": "The width of the bounding box."
          },
          "height": {
            "type": "number",
            "format": "float",
            "description": "The height of the bounding box."
          }
        },
        "description": "Bounding box for an item. It is used for chunks, segments and OCR results."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref4": {
        "type": "object",
        "required": [
          "page_number",
          "page_height",
          "page_width",
          "bbox"
        ],
        "properties": {
          "bbox": {
            "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref3"
          },
          "page_width": {
            "type": "number",
            "format": "float"
          },
          "page_height": {
            "type": "number",
            "format": "float"
          },
          "page_number": {
            "type": "integer",
            "format": "int32",
            "minimum": 0
          }
        },
        "description": "Bbox and page info for one page of a merged multi-page table."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref5": {
        "type": "object",
        "required": [
          "bbox",
          "text"
        ],
        "properties": {
          "bbox": {
            "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref3"
          },
          "link": {
            "type": [
              "string",
              "null"
            ],
            "description": "Optional link URL associated with this OCR result (from PDF annotations)"
          },
          "text": {
            "type": "string",
            "description": "The recognized text of the OCR result."
          },
          "color": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref6",
                "description": "Optional text color (RGB) provided by OCR engine"
              }
            ]
          },
          "confidence": {
            "type": [
              "number",
              "null"
            ],
            "format": "float",
            "description": "The confidence score of the recognized text."
          }
        },
        "description": "OCR results for a segment"
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref6": {
        "type": "object",
        "required": [
          "r",
          "g",
          "b",
          "hex"
        ],
        "properties": {
          "b": {
            "type": "integer",
            "format": "int32"
          },
          "g": {
            "type": "integer",
            "format": "int32"
          },
          "r": {
            "type": "integer",
            "format": "int32"
          },
          "hex": {
            "type": "string"
          }
        },
        "description": "Text color in RGB format"
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref7": {
        "enum": [
          "Caption",
          "Footnote",
          "Formula",
          "KeyValuePair",
          "ListItem",
          "Page",
          "PageFooter",
          "PageHeader",
          "Picture",
          "SectionHeader",
          "Table",
          "Text",
          "Title"
        ],
        "type": "string",
        "description": "All the possible types for a segment.\nNote: Different configurations will produce different types.\nPlease refer to the documentation for more information."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref8": {
        "type": "object",
        "required": [
          "high_resolution",
          "segment_analysis",
          "error_handling"
        ],
        "properties": {
          "model": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref12"
              }
            ]
          },
          "detect_pii": {
            "type": "boolean",
            "description": "When true, run a PII detection pass before parsing. If PII is found, the task is rejected and no parsing occurs."
          },
          "expires_in": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int32",
            "description": "The number of seconds until task is deleted.\nExpired tasks can **not** be updated, polled or accessed via web interface."
          },
          "page_range": {
            "type": [
              "string",
              "null"
            ],
            "description": "Optional page range to process (e.g., \"1-5,8,10-12\"). If None, all pages are processed."
          },
          "json_schema": {
            "deprecated": true
          },
          "excel_config": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref10",
                "description": "Excel-specific config, set only for tasks created via `POST /parse/excel`.\n`None` for every PDF/image/office task. Forwarded to the Excel pipeline service."
              }
            ]
          },
          "merge_tables": {
            "type": "boolean",
            "description": "Whether to merge adjacent tables using VLM"
          },
          "page_numbers": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "type": "integer",
              "format": "int32",
              "minimum": 0
            },
            "description": "Explicit mapping of array indices to actual page numbers (1-based).\nUsed when parsing selective pages (e.g., [4, 5, 8, 9, 10, 11, 12]).\nPopulated from the page_range parameter."
          },
          "xml_citation": {
            "type": "boolean",
            "description": "Whether to extract structured citation data"
          },
          "export_format": {
            "type": [
              "array",
              "null"
            ],
            "items": {
              "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref11"
            },
            "description": "Export format(s) requested for this task. When present, the pipeline generates\nexport files after processing. Currently supported: `[\"docx\"]`."
          },
          "extract_links": {
            "type": "boolean",
            "description": "Whether to extract and apply hyperlink annotations from PDF to OCR results.\nWhen enabled, link URLs from PDF annotations are attached to matching OCR words.\nDefault: false"
          },
          "output_fields": {
            "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref13",
            "description": "Configuration for controlling which output fields are included in responses.\nAllows selective inclusion/exclusion of HTML, Markdown, OCR, images, etc.\nSkipped from the echo when it's the all-true default."
          },
          "error_handling": {
            "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref9"
          },
          "extract_colors": {
            "type": "boolean",
            "description": "Whether to extract and apply color information from PDF text layer to OCR results.\nWhen enabled, text color (RGB/hex) from the PDF is transferred to matching OCR words.\nDefault: false"
          },
          "input_file_url": {
            "type": [
              "string",
              "null"
            ],
            "description": "The presigned URL of the input file."
          },
          "segment_filter": {
            "type": "string",
            "description": "Segment filter: comma-separated segment types to keep, or \"all\".\nReplaces the old metadata-based keep_segment_types storage."
          },
          "high_resolution": {
            "type": "boolean",
            "description": "Whether to use high-resolution images for cropping and post-processing."
          },
          "segment_analysis": {
            "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref14"
          },
          "validate_segments": {
            "type": "array",
            "items": {
              "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref7"
            }
          },
          "target_chunk_length": {
            "type": [
              "integer",
              "null"
            ],
            "format": "int32",
            "minimum": 0,
            "deprecated": true,
            "description": "The target number of words in each chunk. If 0, each chunk will contain a single segment."
          },
          "enhance_reading_order": {
            "type": "boolean",
            "description": "Reorder detected segments to follow the document's natural reading order.\nUseful for multi-column layouts (newspapers, two- or three-column papers).\nDefaults to `false`."
          },
          "extract_strikethrough": {
            "type": "boolean",
            "description": "Preserve strikethrough formatting in HTML/Markdown output. Default: false."
          }
        }
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref9": {
        "enum": [
          "Fail",
          "Continue"
        ],
        "type": "string",
        "description": "Controls how errors are handled during processing:\n- `Fail`: Stops processing and fails the task when any error occurs\n- `Continue`: Attempts to continue processing despite non-critical errors (eg. LLM refusals etc.)"
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref10": {
        "type": "object",
        "properties": {
          "formulas": {
            "type": "boolean",
            "description": "Include cell formulas (only when `cell_metadata`). Default true."
          },
          "dropdowns": {
            "type": "boolean",
            "description": "Include data-validation dropdown options (only when `cell_metadata`). Default true."
          },
          "cell_colors": {
            "type": "boolean",
            "description": "Include cell background/font colors (only when `cell_metadata`). Default true."
          },
          "cell_metadata": {
            "type": "boolean",
            "description": "Include cell color, formula, and dropdown metadata in the output. Default false."
          },
          "exclude_hidden": {
            "type": "boolean",
            "description": "Drop hidden sheets/rows/cols/styling from the output. Default false."
          },
          "exclude_images": {
            "type": "boolean",
            "description": "When excluding hidden content, also drop embedded/pasted images. Default false."
          },
          "exclude_styling": {
            "type": "boolean",
            "description": "When excluding hidden content, also drop styling. Default true."
          },
          "split_large_tables": {
            "type": "boolean",
            "description": "Split large tables into smaller segments. Default true."
          },
          "exclude_hidden_cols": {
            "type": "boolean",
            "description": "When excluding hidden content, also drop hidden columns. Default true."
          },
          "exclude_hidden_rows": {
            "type": "boolean",
            "description": "When excluding hidden content, also drop hidden rows. Default true."
          },
          "max_rows_per_segment": {
            "type": "integer",
            "format": "int32",
            "description": "Max rows per split segment when `split_large_tables`. Default 50."
          },
          "exclude_hidden_sheets": {
            "type": "boolean",
            "description": "When excluding hidden content, also drop hidden sheets. Default true."
          }
        },
        "description": "Excel-specific parsing configuration, forwarded verbatim to the Excel pipeline\nservice (`services/Excel_pipeline` `POST /parse`). These are the ONLY knobs the\nExcel pipeline honors — none of the PDF parsing fields (OCR, layout, segments)\napply. Defaults mirror the service's own `SpreadsheetConfig` defaults so an\nomitted value behaves identically to not setting it. Set on a task via the\ndedicated `POST /parse/excel` endpoint; `None` for every non-Excel task."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref11": {
        "enum": [
          "docx",
          "markdown",
          "json"
        ],
        "type": "string",
        "description": "File format for exporting parsed results. When specified in a parse request,\nthe pipeline generates the requested export file after processing completes.\nThe exported file is available via the `exports` field in the task response."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref12": {
        "enum": [
          "Fast",
          "HighQuality"
        ],
        "type": "string",
        "deprecated": true
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref13": {
        "type": "object",
        "properties": {
          "ocr": {
            "type": "boolean",
            "description": "Include OCR results in segment responses"
          },
          "bbox": {
            "type": "boolean",
            "description": "Include bounding box information in segment responses"
          },
          "html": {
            "type": "boolean",
            "description": "Include HTML representation in segment responses"
          },
          "embed": {
            "type": "boolean",
            "description": "Include embed text in chunk responses"
          },
          "image": {
            "type": "boolean",
            "description": "Include images (cropped segment images) in segment responses"
          },
          "content": {
            "type": "boolean",
            "description": "Include text content in segment responses"
          },
          "markdown": {
            "type": "boolean",
            "description": "Include Markdown representation in segment responses"
          },
          "chart_data": {
            "type": "boolean",
            "description": "Include extracted chart data for Picture segments identified as charts"
          },
          "confidence": {
            "type": "boolean",
            "description": "Include confidence scores in segment responses"
          }
        },
        "description": "Per-field include/exclude filter for the response. Each field defaults to\n`true`; set a field to `false` to drop it."
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref14": {
        "type": "object",
        "properties": {
          "Page": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref17"
              }
            ]
          },
          "Text": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          },
          "Table": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref17"
              }
            ]
          },
          "Title": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          },
          "Caption": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          },
          "Formula": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref17"
              }
            ]
          },
          "Picture": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref18"
              }
            ]
          },
          "Footnote": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          },
          "ListItem": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          },
          "PageFooter": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          },
          "PageHeader": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          },
          "SectionHeader": {
            "oneOf": [
              {
                "type": "null"
              },
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15"
              }
            ]
          }
        }
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref15": {
        "type": "object",
        "properties": {
          "vlm": {
            "type": [
              "string",
              "null"
            ]
          },
          "html": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref16"
              }
            ],
            "default": "Auto"
          },
          "markdown": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref16"
              }
            ],
            "default": "Auto"
          }
        }
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref16": {
        "enum": [
          "VLM",
          "Auto"
        ],
        "type": "string"
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref17": {
        "type": "object",
        "properties": {
          "vlm": {
            "type": [
              "string",
              "null"
            ],
            "description": "Prompt for the VLM model"
          },
          "html": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref16"
              }
            ],
            "default": "VLM"
          },
          "markdown": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref16"
              }
            ],
            "default": "VLM"
          }
        }
      },
      "sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref18": {
        "type": "object",
        "properties": {
          "vlm": {
            "type": [
              "string",
              "null"
            ],
            "description": "Prompt for the VLM model"
          },
          "html": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref16"
              }
            ],
            "default": "Auto"
          },
          "markdown": {
            "oneOf": [
              {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref16"
              }
            ],
            "default": "Auto"
          },
          "transcribe_text": {
            "type": "boolean",
            "default": false,
            "description": "When true, text-bearing pictures (forms, handwritten pages, scanned\ndocuments, screenshots of text) are transcribed verbatim by the VLM\ninstead of described/summarized. Only takes effect for segments that\nactually contain OCR text — true figures (photos, charts, diagrams with\nlittle text) still get the standard description. Default: false."
          }
        }
      }
    }
  },
  "paths": {
    "/classify": {
      "post": {
        "summary": "Classify Document",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "job_id": {
                      "type": "string",
                      "description": "Pass to GET /classify/{job_id}."
                    },
                    "status": {
                      "type": "string",
                      "description": "processing on creation."
                    },
                    "message": {
                      "type": "string"
                    },
                    "quota_remaining": {
                      "type": "number"
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "202": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "job_id": {
                      "type": "string",
                      "description": "Unique identifier for the classification job"
                    },
                    "status": {
                      "type": "string",
                      "description": "Current job status (typically 'processing')"
                    },
                    "message": {
                      "type": "string",
                      "description": "Status message about the job"
                    },
                    "quota_remaining": {
                      "type": "number",
                      "description": "Remaining API quota after this request"
                    }
                  }
                }
              }
            },
            "description": "Accepted - classification job started"
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          }
        },
        "parameters": [],
        "description": "Creates a classification job for a PDF or image (JPG, PNG, GIF, WebP, BMP, TIFF) given by URL, with the list of candidate category names, and returns the job id at once. Poll GET /classify/{job_id} for the dominant category, its confidence, every category present with the pages that voted for it, and per-page results. Documents longer than four pages are classified from their first four. Usage is the page count of the document.",
        "operationId": "classifyDocument",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "example": {
                  "file_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
                  "categories": "[{\"name\":\"invoice\"},{\"name\":\"contract\"},{\"name\":\"other\"}]"
                },
                "required": [
                  "file_url",
                  "categories"
                ],
                "properties": {
                  "document": {
                    "type": "string",
                    "description": "The document file (PDF or image) to classify."
                  },
                  "file_url": {
                    "type": "string",
                    "format": "uri",
                    "description": "Public or presigned URL of the PDF or image to classify."
                  },
                  "categories": {
                    "type": "string",
                    "items": {
                      "type": "string"
                    },
                    "description": "JSON-encoded array of category objects, each with a required name, for example [{\"name\":\"invoice\"},{\"name\":\"contract\"}]. Descriptions are accepted but only the names guide the result, sent as a string."
                  }
                }
              }
            },
            "multipart/form-data": {
              "schema": {
                "type": "object",
                "required": [
                  "categories"
                ],
                "properties": {
                  "file_url": {
                    "type": "string",
                    "description": "URL to a document to classify (PDF or image). Provide either pdf_file or file_url, not both."
                  },
                  "pdf_file": {
                    "type": "string",
                    "format": "binary",
                    "description": "The document to classify: a PDF or an image (JPG, PNG, GIF, WebP, BMP, TIFF). Provide either pdf_file or file_url, not both. Maximum file size: 500MB."
                  },
                  "categories": {
                    "type": "string",
                    "description": "JSON string containing an array of category objects with a required name. Example: [{\"name\":\"invoice\"},{\"name\":\"contract\"},{\"name\":\"receipt\"}]. A \"description\" key is accepted for compatibility but is not used by classification."
                  }
                }
              }
            }
          },
          "required": true
        },
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_cES-1nNgXX2BgZl6bugel",
            "authority": "supplemental",
            "conflicts": [
              "/description"
            ],
            "revisionId": "sdrn_Igz2_6J8nS2tNfjrFM1LY"
          },
          {
            "gaps": [
              "Missing requestBody schema",
              "Missing response schema"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [
              "Missing explicit schema for response body fields.",
              "Missing explicit media type for document upload (e.g., multipart/form-data vs base64)."
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_rQ8XkWDBlF8PRpWQ8rxaS",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/requestBody/content/application/json/schema/required",
              "/requestBody/content/application/json/schema/properties/categories/type",
              "/requestBody/content/application/json/schema/properties/categories/description"
            ],
            "revisionId": "sdrn_Rubn_SliKnniHL51onOUn"
          },
          {
            "gaps": [
              "Missing request body schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description",
              "/requestBody/content/application/json/schema/required",
              "/requestBody/content/application/json/schema/properties/document/description",
              "/requestBody/content/application/json/schema/properties/categories/type"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          }
        ],
        "x-zeroclick-services": [
          "classify"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "20000",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "$0.020000 per page (pages, service classify)",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.020000"
          },
          "rates": [
            {
              "service": "classify",
              "meter": "pages",
              "unit": "page",
              "unitSize": 1,
              "priceUsd": "0.020000",
              "includedUnits": 0
            }
          ]
        }
      }
    },
    "/classify/{job_id}": {
      "get": {
        "summary": "Get Classification Job Status",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "error": {
                      "type": "string",
                      "nullable": true,
                      "description": "Error message if job failed"
                    },
                    "job_id": {
                      "type": "string",
                      "description": "Unique identifier for the classification job"
                    },
                    "result": {
                      "type": "object",
                      "nullable": true,
                      "properties": {
                        "success": {
                          "type": "boolean",
                          "description": "Whether classification succeeded"
                        },
                        "categories": {
                          "type": "array",
                          "items": {
                            "type": "object",
                            "properties": {
                              "pages": {
                                "type": "array",
                                "items": {
                                  "type": "integer"
                                }
                              },
                              "category": {
                                "type": "string"
                              },
                              "confidence": {
                                "type": "number"
                              },
                              "page_count": {
                                "type": "integer"
                              }
                            }
                          }
                        },
                        "confidence": {
                          "type": "number",
                          "description": "Confidence score (0-1)"
                        },
                        "total_pages": {
                          "type": "integer",
                          "description": "Total number of pages"
                        },
                        "page_results": {
                          "type": "array",
                          "items": {
                            "type": "object",
                            "properties": {
                              "page": {
                                "type": "integer",
                                "description": "Page number"
                              },
                              "success": {
                                "type": "boolean",
                                "description": "Whether this page was classified successfully"
                              },
                              "confidence": {
                                "type": "number",
                                "description": "Confidence score for this page"
                              },
                              "raw_result": {
                                "type": "string",
                                "description": "The model's raw classification output for this page"
                              },
                              "classification": {
                                "type": "string",
                                "description": "Classification for this page"
                              }
                            }
                          },
                          "description": "Per-page classification results"
                        },
                        "classification": {
                          "type": "string",
                          "description": "The classified category"
                        },
                        "processed_pages": {
                          "type": "integer",
                          "description": "Number of pages processed"
                        }
                      },
                      "description": "Classification results (only present when status is completed)"
                    },
                    "status": {
                      "enum": [
                        "queued",
                        "processing",
                        "completed",
                        "failed"
                      ],
                      "type": "string",
                      "description": "Current job status (queued, processing, completed, failed)"
                    },
                    "progress": {
                      "type": "string",
                      "description": "Progress message"
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          }
        },
        "parameters": [
          {
            "in": "path",
            "name": "job_id",
            "schema": {
              "type": "string",
              "format": "uuid"
            },
            "example": "04a7a6d8-5ef7-465a-b22a-8a98e7104dd9",
            "required": true,
            "description": "Job id returned by POST /classify."
          }
        ],
        "description": "Check the status and progress of classification jobs and retrieve results",
        "operationId": "getClassificationStatus",
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/content/application/json/schema/properties/result/properties/total_pages/type",
              "/responses/200/content/application/json/schema/properties/result/properties/page_results/items/properties/page/type",
              "/responses/200/content/application/json/schema/properties/result/properties/processed_pages/type",
              "/responses/200/description",
              "/parameters/path/job_id/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_SS0eeS5B4SaXbN_-m89B6",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/content/application/json/schema/properties/result/properties/total_pages/type",
              "/responses/200/content/application/json/schema/properties/result/properties/page_results/items/properties/page/type",
              "/responses/200/content/application/json/schema/properties/result/properties/processed_pages/type",
              "/responses/200/description",
              "/parameters/path/job_id/description"
            ],
            "revisionId": "sdrn_SW9iGwZVd6388LMjtutR6"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          }
        ],
        "x-zeroclick-services": [
          "classify"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "0",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "Free",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.000000"
          }
        }
      }
    },
    "/extract/{job_id}": {
      "get": {
        "summary": "Get Extraction Job Status",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "error": {
                      "type": "string",
                      "nullable": true
                    },
                    "job_id": {
                      "type": "string"
                    },
                    "result": {
                      "type": "object",
                      "description": "One key per schema field.",
                      "additionalProperties": {
                        "type": "object",
                        "properties": {
                          "score": {
                            "type": "object",
                            "properties": {
                              "grounding_score": {
                                "type": "number"
                              },
                              "extraction_score": {
                                "type": "number",
                                "nullable": true
                              }
                            }
                          },
                          "value": {
                            "description": "The extracted value in the schema type."
                          },
                          "citation": {
                            "type": "object",
                            "nullable": true,
                            "properties": {
                              "bbox": {
                                "type": "array",
                                "items": {
                                  "type": "number"
                                }
                              },
                              "page": {
                                "type": "integer"
                              },
                              "page_width": {
                                "type": "number"
                              },
                              "page_height": {
                                "type": "number"
                              }
                            }
                          }
                        }
                      }
                    },
                    "status": {
                      "enum": [
                        "queued",
                        "processing",
                        "completed",
                        "review",
                        "failed"
                      ],
                      "type": "string"
                    },
                    "file_url": {
                      "type": "string",
                      "nullable": true,
                      "description": "Presigned link to the uploaded document, valid about an hour."
                    },
                    "metadata": {
                      "type": "object",
                      "properties": {
                        "order": {
                          "type": "array",
                          "items": {
                            "type": "string"
                          }
                        },
                        "schema": {
                          "type": "object"
                        },
                        "page_count": {
                          "type": "integer"
                        }
                      }
                    },
                    "file_name": {
                      "type": "string",
                      "nullable": true
                    },
                    "created_at": {
                      "type": "string",
                      "format": "date-time"
                    },
                    "updated_at": {
                      "type": "string",
                      "format": "date-time"
                    }
                  },
                  "description": "Extraction job status and results"
                }
              }
            },
            "description": "Successful response"
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          },
          "429": {
            "description": "Too many requests"
          },
          "503": {
            "description": "Service unavailable"
          }
        },
        "parameters": [
          {
            "in": "path",
            "name": "job_id",
            "schema": {
              "type": "string",
              "format": "uuid"
            },
            "example": "04a7a6d8-5ef7-465a-b22a-8a98e7104dd9",
            "required": true,
            "description": "Job id returned by POST /v2/extract."
          }
        ],
        "description": "Check the status and retrieve results of extraction jobs",
        "operationId": "getExtractJob",
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/parameters/path/job_id/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [
              "Missing full response schema for job object",
              "Missing request headers definition"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_Hpa9dC7c1a9aN7gjDFk36",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_oNuLNtRxtzvC8-FGU4kjB"
          },
          {
            "gaps": [
              "Missing full response schema for GET /extract/{job_id}"
            ],
            "pages": [
              14
            ],
            "sourceId": "sds_kaK4CHFpMuf2E4eiG8lYb",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_1-Xtdh3_uFZoAztsI3pVM"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/operationId"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_PSN7metklPNzycVnbW3ia",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/parameters/path/job_id/description"
            ],
            "revisionId": "sdrn_cEfQuuOgB_ia42zwFCOaE"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          }
        ],
        "x-zeroclick-services": [
          "extract"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "0",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "Free",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.000000"
          }
        }
      }
    },
    "/parse": {
      "post": {
        "summary": "Parse Document",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_c8cef78e290bd936_ref2",
                  "type": "object",
                  "properties": {
                    "job_id": {
                      "type": "string",
                      "description": "Pass to GET /parse/{job_id}."
                    },
                    "status": {
                      "type": "string",
                      "description": "Starting on creation."
                    },
                    "message": {
                      "type": "string",
                      "description": "Status message about the job creation"
                    },
                    "file_name": {
                      "type": "string",
                      "description": "Name of the uploaded file"
                    },
                    "created_at": {
                      "type": "string",
                      "format": "date-time",
                      "description": "Timestamp when the job was created"
                    },
                    "credit_used": {
                      "type": "integer",
                      "description": "Pages counted for this job."
                    },
                    "merge_tables": {
                      "type": "boolean",
                      "description": "Whether table merging is enabled"
                    },
                    "quota_remaining": {
                      "type": "integer",
                      "description": "Remaining page quota for the API key"
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "400": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Bad request — missing file/url, unsupported file type, or invalid parameters."
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          },
          "403": {
            "description": "Forbidden — access has been revoked."
          },
          "429": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Usage limit exceeded (billing cap) or rate limit hit (see the Rate Limits reference)."
          },
          "500": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Internal server error."
          },
          "503": {
            "description": "Service unavailable — job queue is at capacity. Retry after the duration indicated in the `Retry-After` header."
          }
        },
        "parameters": [],
        "description": "Creates a parse job for a PDF, DOCX, JPEG, PNG, WEBP or PPTX document sent by URL, and returns the job id at once. Other formats are converted to PDF first. Poll GET /parse/{job_id} for the ordered chunks with Markdown, HTML, OCR text, bounding boxes and confidence per segment. Options select the layout model, OCR engine, page range, output fields and exports. Excel workbooks go to POST /parse/excel. Usage is the page count of the document.",
        "operationId": "create_parse_task",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_c8cef78e290bd936_ref0",
                "type": "object",
                "example": {
                  "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
                },
                "required": [
                  "url"
                ],
                "properties": {
                  "url": {
                    "type": "string",
                    "format": "uri",
                    "description": "Public or presigned URL of the document to process."
                  },
                  "detect_pii": {
                    "type": "boolean",
                    "default": false,
                    "description": "Run a PII detection pass first. When PII at or above pii_block_severity is found the job is not created and the response says so."
                  },
                  "ocr_engine": {
                    "enum": [
                      "UnsiloedHawk",
                      "UnsiloedBeta",
                      "UnsiloedStorm"
                    ],
                    "type": "string",
                    "description": "OCR engine: Hawk for complex layouts and mixed content (the documented default), Beta for rotated or warped text, Storm for 50 plus languages."
                  },
                  "page_range": {
                    "type": "string",
                    "description": "Pages to process, for example 1-5, 2,4,6 or [1,3,5]. Defaults to all pages."
                  },
                  "pii_engine": {
                    "enum": [
                      "standard",
                      "advanced"
                    ],
                    "type": "string",
                    "default": "standard",
                    "description": "PII detector: standard is the fast pattern engine, advanced has higher precision."
                  },
                  "agentic_ocr": {
                    "enum": [
                      "standard",
                      "advanced"
                    ],
                    "type": "string",
                    "description": "Re-reads each segment with an agentic OCR model after layout detection for higher accuracy; omit to disable."
                  },
                  "merge_tables": {
                    "type": "boolean",
                    "default": false,
                    "description": "Stitch tables that continue across page breaks into one table by matching headers and columns."
                  },
                  "ocr_strategy": {
                    "enum": [
                      "auto_detection",
                      "force_ocr"
                    ],
                    "type": "string",
                    "default": "auto_detection",
                    "description": "auto_detection runs OCR only where the page needs it; force_ocr runs it on every page."
                  },
                  "xml_citation": {
                    "type": "boolean",
                    "default": false,
                    "description": "Extract the bibliography of a research PDF and hyperlink in-text citations in the Markdown. PDFs only."
                  },
                  "export_format": {
                    "type": "array",
                    "items": {
                      "enum": [
                        "docx",
                        "markdown",
                        "json"
                      ],
                      "type": "string"
                    },
                    "description": "Export files to generate after parsing; their download links appear in the exports field of the result."
                  },
                  "extract_links": {
                    "type": "boolean",
                    "default": false,
                    "description": "Attach hyperlink URLs from PDF annotations to the OCR results."
                  },
                  "output_fields": {
                    "type": "string",
                    "description": "JSON-encoded object of booleans to drop fields from each segment: html, markdown, ocr, image, content, bbox, confidence, embed, chart_data. All default to true."
                  },
                  "error_handling": {
                    "enum": [
                      "Continue",
                      "Fail"
                    ],
                    "type": "string",
                    "default": "Continue",
                    "description": "Continue skips segments that fail (for example a model refusal); Fail stops the job on the first error."
                  },
                  "extract_colors": {
                    "type": "boolean",
                    "default": false,
                    "description": "Carry text colour from the PDF text layer into the OCR results."
                  },
                  "segment_filter": {
                    "type": "string",
                    "default": "all",
                    "description": "Comma-separated segment types to keep (table, picture, formula, text, sectionheader, title, listitem, caption, footnote, pageheader, pagefooter, keyvaluepair, signature, seal, page) or all."
                  },
                  "layout_analysis": {
                    "enum": [
                      "smart_layout_detection",
                      "page_by_page",
                      "advanced_layout_detection"
                    ],
                    "type": "string",
                    "default": "smart_layout_detection",
                    "description": "How pages are segmented: smart_layout_detection finds headers, sections, tables and figures with bounding boxes; page_by_page treats each page as one segment (fastest); advanced_layout_detection runs a vision model for dense or unusual layouts."
                  },
                  "merge_batch_size": {
                    "type": "integer",
                    "default": 20,
                    "minimum": 2,
                    "description": "Most tables per merge group when merge_tables is on."
                  },
                  "response_profile": {
                    "enum": [
                      "slim",
                      "full",
                      "custom"
                    ],
                    "type": "string",
                    "description": "slim returns only embed text, bbox, page number, segment id and type plus HTML for tables or Markdown for the rest; full returns everything; custom honours output_fields."
                  },
                  "segment_analysis": {
                    "type": "string",
                    "description": "JSON-encoded object setting, per segment type, whether HTML and Markdown come from a vision model (VLM) or straight from OCR (Auto), the model id, a custom prompt and optional translation. See the Unsiloed parse reference for the per-type defaults."
                  },
                  "validate_segments": {
                    "type": "string",
                    "description": "JSON-encoded array of segment types to re-check with a vision model, for example [\"Table\",\"Formula\",\"Picture\"]. Defaults to Table and Picture."
                  },
                  "pii_block_severity": {
                    "enum": [
                      "any",
                      "low",
                      "medium",
                      "high"
                    ],
                    "type": "string",
                    "default": "any",
                    "description": "Severity that blocks the job when detect_pii is on: any finding, quasi-identifiers (names, dates, locations), contact details (email, phone), or direct identifiers only (SSN, passport, card numbers)."
                  },
                  "segment_type_naming": {
                    "enum": [
                      "Unsiloed",
                      "Other"
                    ],
                    "type": "string",
                    "default": "Unsiloed",
                    "description": "Segment type names: Unsiloed (PageHeader, ListItem, Picture) or Other (Header, List Item, Figure)."
                  },
                  "use_high_resolution": {
                    "type": "boolean",
                    "description": "Use high-resolution page images for cropping and OCR. Better on poor scans, about 2 to 3 seconds more per page."
                  },
                  "segmentation_version": {
                    "enum": [
                      "v1",
                      "v2"
                    ],
                    "type": "string",
                    "default": "v1",
                    "description": "Layout model. v2 is form-aware and also returns KeyValuePair, Signature and Seal segments; use it for forms and applications."
                  },
                  "enhance_reading_order": {
                    "type": "boolean",
                    "default": false,
                    "description": "Reorder segments into natural reading order; recommended for multi-column layouts. No effect with page_by_page."
                  },
                  "extract_strikethrough": {
                    "type": "boolean",
                    "default": false,
                    "description": "Keep strikethrough formatting in the HTML and Markdown output."
                  }
                }
              }
            },
            "multipart/form-data": {
              "schema": {
                "type": "object",
                "required": [
                  "file"
                ],
                "properties": {
                  "url": {
                    "type": "string",
                    "nullable": true,
                    "description": "Presigned or public URL of the document to fetch and process.\nRequired if `file` is not provided."
                  },
                  "file": {
                    "type": "string",
                    "format": "binary",
                    "description": "Supported file types: PDFs, Images (PNG, JPEG, TIFF, BMP) and Office Documents (DOCX, XLSX, PPTX)"
                  },
                  "mode": {
                    "enum": [
                      "fast",
                      "agentic_lite",
                      "agentic"
                    ],
                    "type": "string",
                    "nullable": true,
                    "description": "Processing mode preset. `fast` (Fast), `agentic_lite` (Agentic Lite), or `agentic` (Agentic). Each mode applies a recommended processing configuration; see [Processing Modes](/document-processing/parsing/processing-modes). Parameters you send explicitly take precedence over the mode. Omit to use the default configuration."
                  },
                  "detect_pii": {
                    "type": "boolean",
                    "default": false,
                    "nullable": true,
                    "description": "Run a PII detection pass before parsing. If PII is found, the task is rejected and no parsing occurs. Defaults to false."
                  },
                  "expires_in": {
                    "type": "integer",
                    "format": "int32",
                    "nullable": true,
                    "description": "Seconds until the task and its output are deleted. Defaults to the plan expiration time."
                  },
                  "ocr_engine": {
                    "type": "string"
                  },
                  "page_range": {
                    "type": "string",
                    "nullable": true,
                    "description": "Page range to process. Formats: `\"1-5\"`, `\"2,4,6\"`, `\"[1,3,5]\"`. Defaults to all pages."
                  },
                  "agentic_ocr": {
                    "type": "string"
                  },
                  "merge_tables": {
                    "type": "boolean",
                    "default": false,
                    "nullable": true,
                    "description": "Whether to merge adjacent table segments (default: false)"
                  },
                  "ocr_strategy": {
                    "type": "string"
                  },
                  "xml_citation": {
                    "type": "boolean",
                    "default": false,
                    "nullable": true,
                    "description": "Enable citation extraction from PDF documents. Extracts structured bibliography and hyperlinks in-text citations in markdown output (default: false)"
                  },
                  "export_format": {
                    "type": "array",
                    "items": {
                      "enum": [
                        "docx",
                        "markdown",
                        "json"
                      ],
                      "type": "string"
                    },
                    "example": [
                      "docx",
                      "markdown",
                      "json"
                    ],
                    "nullable": true,
                    "description": "Export format(s) to generate after processing.\nWhen set, the pipeline generates the requested export files after parsing completes.\nThe exported files are available as presigned URLs in the `exports` field of the response.\nSupported: `[\"docx\", \"markdown\", \"json\"]`."
                  },
                  "extract_links": {
                    "type": "boolean",
                    "default": false,
                    "nullable": true,
                    "description": "Attach hyperlink URLs from PDF annotations to OCR results. Defaults to `false`."
                  },
                  "output_fields": {
                    "type": "string",
                    "nullable": true,
                    "description": "JSON object controlling which output fields are included in the response.\nExample: `{\"html\": false, \"markdown\": true, \"ocr\": false}`.\nAll fields default to `true`."
                  },
                  "error_handling": {
                    "type": "string",
                    "default": "Continue",
                    "nullable": true,
                    "description": "Error handling strategy for non-critical processing errors.\n`Continue` (default) — proceed despite errors (e.g., LLM refusals).\n`Fail` — stop and fail the task on any error."
                  },
                  "extract_charts": {
                    "enum": [
                      "basic",
                      "standard",
                      "advanced"
                    ],
                    "type": "string",
                    "default": "basic",
                    "nullable": true,
                    "description": "Digitize charts into the numbers they were drawn from, attached to the Picture segment as `chart_data`. `basic` (default): no chart data. `standard`: fast and accurate chart data extraction. `advanced`: for the most complex and messiest charts; contact support to have it enabled for your organization (otherwise `403` with `error.code` = `feature_not_enabled`)."
                  },
                  "extract_colors": {
                    "type": "boolean",
                    "default": false,
                    "nullable": true,
                    "description": "Transfer text color from the PDF text layer to OCR results. Defaults to `false`."
                  },
                  "segment_filter": {
                    "type": "string",
                    "default": "all",
                    "nullable": true,
                    "description": "Filter output to include only specific segment types. Accepts comma-separated list (e.g., 'table', 'picture', 'table,picture') or 'all' for everything (default: 'all')"
                  },
                  "segment_analysis": {
                    "type": "string",
                    "nullable": true,
                    "description": "JSON object controlling HTML/Markdown generation and custom VLM prompts per segment type.\nExample: `{\"Table\": {\"html\": \"VLM\", \"vlm\": \"Preserve merged cells.\"}}`."
                  },
                  "validate_segments": {
                    "type": "string",
                    "nullable": true,
                    "description": "JSON array string of segment types to validate with VLM.\nExample: `[\"Table\", \"Formula\", \"Picture\"]`. Defaults to `[\"Table\", \"Picture\"]`; an empty or unparseable value also falls back to that default."
                  },
                  "segment_processing": {
                    "type": "string"
                  },
                  "segmentation_version": {
                    "type": "string"
                  },
                  "enhance_reading_order": {
                    "type": "boolean",
                    "default": false,
                    "nullable": true,
                    "description": "Reorder detected segments to follow the document's natural reading order.\nUseful for multi-column layouts (newspapers, two- or three-column papers).\nDefaults to `false`."
                  },
                  "extract_strikethrough": {
                    "type": "boolean",
                    "default": false,
                    "nullable": true,
                    "description": "Preserve strikethrough formatting in HTML/Markdown output. Defaults to `false`."
                  }
                },
                "description": "Request body for `POST /parse` (multipart/form-data).\n\nProvide either `file` (binary upload) or `url` (presigned/public URL) — not both."
              },
              "encoding": {
                "file": {
                  "contentType": "application/octet-stream"
                }
              }
            }
          },
          "required": true,
          "description": "Multipart form data. Provide either `file` (binary upload) or `url` (presigned/public URL), not both."
        },
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/content/application/json/schema/properties/job_id/description",
              "/responses/200/content/application/json/schema/properties/status/description",
              "/responses/200/content/application/json/schema/properties/quota_remaining/type",
              "/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_NhuZy9GOUeiFES-p8ND-N",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/requestBody/content/multipart/form-data/schema/properties/file/description",
              "/requestBody/content/multipart/form-data/schema/properties/merge_tables/description",
              "/requestBody/content/multipart/form-data/schema/properties/xml_citation/description",
              "/requestBody/content/multipart/form-data/schema/properties/segment_filter/description"
            ],
            "revisionId": "sdrn_y0k53_WIaoH6uXy4qWS0v"
          },
          {
            "gaps": [
              "Missing detailed schema for response body fields in documentation text, though structure is implied by examples."
            ],
            "pages": [
              1,
              2,
              3,
              4,
              5,
              6,
              7,
              8,
              9,
              10,
              11,
              12,
              13,
              14,
              15,
              16,
              17,
              18,
              19,
              20
            ],
            "sourceId": "sds_5mKZ7u4EuMmqMPpkxuqwQ",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_3aXHDqzqz34z_QepzFlix"
          },
          {
            "gaps": [
              "Missing explicit parameter definitions for presigned URL input",
              "Missing full response schema for job status polling"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_8VSEvjmXbbPhvOOwxMOcF",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_QKAZs3PUrondGuVmzlhew"
          },
          {
            "gaps": [
              "Missing requestBody schema",
              "Missing response schema"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/operationId"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [
              "The documentation provides examples using multipart/form-data with stringified JSON for segment_processing, but does not explicitly define the full schema for the segment_processing object."
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_SmAnIAFZQ8CAU7pF_Fgmg",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId",
              "/requestBody/content/multipart/form-data/schema/properties/merge_tables/type"
            ],
            "revisionId": "sdrn_1_ZSxhqDh8CgcUBpLg5V9"
          },
          {
            "gaps": [],
            "pages": [
              1,
              2
            ],
            "sourceId": "sds_t9ntEcaThNlHLT-QQlldu",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_vOTBsnn3yZ9S3CfIyU2oq"
          },
          {
            "gaps": [
              "Missing requestBody schema details",
              "Missing response schema details"
            ],
            "pages": [
              41
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          },
          {
            "gaps": [
              "Missing full response schema for /parse/{job_id} polling endpoint",
              "Missing documentation for other optional parameters mentioned in the note"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_XenLvVnJsQQESm6TWWjg0",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId",
              "/requestBody/content/multipart/form-data/schema/required",
              "/requestBody/content/multipart/form-data/schema/properties/url/description"
            ],
            "revisionId": "sdrn_x2iFA9dn9FPJBr1zpKrlu"
          }
        ],
        "x-zeroclick-services": [
          "parse"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "20000",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "$0.020000 per page (pages, service parse)",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.020000"
          },
          "rates": [
            {
              "service": "parse",
              "meter": "pages",
              "unit": "page",
              "unitSize": 1,
              "priceUsd": "0.020000",
              "includedUnits": 0
            }
          ]
        }
      }
    },
    "/parse/excel": {
      "post": {
        "summary": "POST /parse/excel",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_fd7fdafe238897e0_ref1",
                  "type": "object",
                  "properties": {
                    "job_id": {
                      "type": "string",
                      "description": "Pass to GET /parse/{job_id}."
                    },
                    "status": {
                      "type": "string",
                      "description": "Starting on creation."
                    },
                    "message": {
                      "type": "string"
                    },
                    "file_name": {
                      "type": "string"
                    },
                    "created_at": {
                      "type": "string",
                      "format": "date-time"
                    },
                    "credit_used": {
                      "type": "integer",
                      "description": "Pages counted for this job."
                    },
                    "merge_tables": {
                      "type": "boolean",
                      "description": "Always false for workbooks."
                    },
                    "quota_remaining": {
                      "type": "integer"
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "400": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Bad request — missing file/url, non-Excel file type, or invalid parameters."
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          },
          "403": {
            "description": "Forbidden — access has been revoked."
          },
          "429": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Usage limit exceeded (billing cap) or rate limit hit."
          },
          "500": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Internal server error."
          },
          "503": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Service unavailable — job queue is at capacity."
          }
        },
        "parameters": [],
        "description": "Creates a parse job for an XLS or XLSX workbook given by URL, and returns the job id at once. Poll GET /parse/{job_id} for the result: every detected table as a segment with cell-range references back to the sheet, large tables split into row blocks. Options drop hidden sheets, rows, columns, styling and images and tune table detection. Usage is the page count of the workbook, where 5,000 by 5,000 cells count as one page.",
        "operationId": "create_parse_task_excel",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "example": {
                  "url": "https://download.microsoft.com/download/1/4/E/14EDED28-6C58-4055-A65C-23B4DA81C4DE/Financial%20Sample.xlsx"
                },
                "required": [
                  "url"
                ],
                "properties": {
                  "url": {
                    "type": "string",
                    "format": "uri",
                    "description": "Public or presigned URL of the XLS or XLSX workbook."
                  },
                  "exclude_hidden": {
                    "type": "boolean",
                    "default": false,
                    "description": "Drop hidden content from the output. The five toggles below apply only when this is true."
                  },
                  "exclude_images": {
                    "type": "boolean",
                    "default": false,
                    "description": "Also drop embedded and pasted images."
                  },
                  "exclude_styling": {
                    "type": "boolean",
                    "default": true,
                    "description": "Also drop cell styling."
                  },
                  "table_clustering": {
                    "enum": [
                      "accurate",
                      "fast",
                      "off"
                    ],
                    "type": "string",
                    "default": "accurate",
                    "description": "How hard to look for distinct logical tables on one sheet: accurate, fast (may merge nearby tables) or off (one table per sheet)."
                  },
                  "split_large_tables": {
                    "type": "boolean",
                    "default": true,
                    "description": "Split large tables into smaller segments."
                  },
                  "exclude_hidden_cols": {
                    "type": "boolean",
                    "default": true,
                    "description": "Also drop hidden columns from visible sheets."
                  },
                  "exclude_hidden_rows": {
                    "type": "boolean",
                    "default": true,
                    "description": "Also drop hidden rows from visible sheets."
                  },
                  "max_rows_per_segment": {
                    "type": "integer",
                    "default": 50,
                    "minimum": 1,
                    "description": "Rows per segment when split_large_tables is on."
                  },
                  "exclude_hidden_sheets": {
                    "type": "boolean",
                    "default": true,
                    "description": "Also drop entire hidden sheets."
                  }
                }
              }
            },
            "multipart/form-data": {
              "schema": {
                "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_fd7fdafe238897e0_ref0",
                "type": "object",
                "properties": {
                  "url": {
                    "type": "string",
                    "description": "URL to a workbook in cloud storage"
                  },
                  "file": {
                    "type": "string",
                    "format": "binary",
                    "description": "Excel file upload"
                  },
                  "expires_in": {
                    "type": "integer"
                  },
                  "exclude_hidden": {
                    "enum": [
                      "true",
                      "false"
                    ],
                    "type": "string",
                    "description": "Drop hidden sheets, rows, columns, and styling"
                  },
                  "exclude_images": {
                    "enum": [
                      "true",
                      "false"
                    ],
                    "type": "string"
                  },
                  "exclude_styling": {
                    "type": "boolean"
                  },
                  "table_clustering": {
                    "enum": [
                      "accurate",
                      "fast",
                      "off"
                    ],
                    "type": "string"
                  },
                  "split_large_tables": {
                    "enum": [
                      "true",
                      "false"
                    ],
                    "type": "string"
                  },
                  "exclude_hidden_cols": {
                    "enum": [
                      "true",
                      "false"
                    ],
                    "type": "string"
                  },
                  "exclude_hidden_rows": {
                    "enum": [
                      "true",
                      "false"
                    ],
                    "type": "string"
                  },
                  "max_rows_per_segment": {
                    "type": "integer"
                  },
                  "exclude_hidden_sheets": {
                    "enum": [
                      "true",
                      "false"
                    ],
                    "type": "string"
                  }
                }
              }
            }
          },
          "required": true,
          "description": "Provide either `file` (binary .xls/.xlsx upload, multipart only) or `url` (presigned/public URL, both content types), not both. The `file` field is multipart-only. Excel parsing uses its own config — PDF parsing options do not apply."
        },
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_NhuZy9GOUeiFES-p8ND-N",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_y0k53_WIaoH6uXy4qWS0v"
          },
          {
            "gaps": [
              "The documentation specifies boolean parameters are sent as strings 'true'/'false' in multipart form, but does not explicitly define the schema as a JSON object for the multipart body."
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_4aYX6deVDwgqAdWOHetp7",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId",
              "/requestBody/required"
            ],
            "revisionId": "sdrn_fliIi28Ma5mldFeoERKlY"
          },
          {
            "gaps": [
              "Missing detailed request/response schema"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_8VSEvjmXbbPhvOOwxMOcF",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_QKAZs3PUrondGuVmzlhew"
          },
          {
            "gaps": [
              "Missing requestBody schema",
              "Missing response schema"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/operationId"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_teO5HknDJlGYJT3yP3d6w",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/responses/402/description",
              "/responses/403/description",
              "/responses/429/description",
              "/description",
              "/requestBody/content/multipart/form-data/schema/properties/exclude_hidden/type",
              "/requestBody/content/multipart/form-data/schema/properties/exclude_images/type",
              "/requestBody/content/multipart/form-data/schema/properties/split_large_tables/type",
              "/requestBody/content/multipart/form-data/schema/properties/exclude_hidden_cols/type",
              "/requestBody/content/multipart/form-data/schema/properties/exclude_hidden_rows/type",
              "/requestBody/content/multipart/form-data/schema/properties/exclude_hidden_sheets/type"
            ],
            "revisionId": "sdrn_S_vn0SHSKp6DZzmQ-gWci"
          },
          {
            "gaps": [
              "Missing requestBody schema details",
              "Missing response schema details"
            ],
            "pages": [
              42
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          }
        ],
        "x-zeroclick-services": [
          "parse"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "20000",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "$0.020000 per page (pages, service parse)",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.020000"
          },
          "rates": [
            {
              "service": "parse",
              "meter": "pages",
              "unit": "page",
              "unitSize": 1,
              "priceUsd": "0.020000",
              "includedUnits": 0
            }
          ]
        }
      }
    },
    "/parse/{job_id}": {
      "get": {
        "summary": "Get Parse Job Status",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/sds_NhuZy9GOUeiFES-p8ND-N_4caee2d8a2406dfe_ref0",
                  "type": "object",
                  "properties": {
                    "chunks": {
                      "type": "array",
                      "items": {
                        "type": "object",
                        "properties": {
                          "embed": {
                            "type": "string",
                            "description": "Text to embed for retrieval."
                          },
                          "chunk_id": {
                            "type": "string"
                          },
                          "segments": {
                            "type": "array",
                            "items": {
                              "type": "object",
                              "properties": {
                                "ocr": {
                                  "type": "array",
                                  "items": {
                                    "type": "object",
                                    "properties": {
                                      "bbox": {
                                        "type": "object"
                                      },
                                      "text": {
                                        "type": "string"
                                      },
                                      "confidence": {
                                        "type": "number"
                                      }
                                    }
                                  }
                                },
                                "bbox": {
                                  "type": "object",
                                  "properties": {
                                    "top": {
                                      "type": "number"
                                    },
                                    "left": {
                                      "type": "number"
                                    },
                                    "width": {
                                      "type": "number"
                                    },
                                    "height": {
                                      "type": "number"
                                    }
                                  }
                                },
                                "html": {
                                  "type": "string"
                                },
                                "image": {
                                  "type": "string",
                                  "nullable": true,
                                  "description": "Presigned crop link, null unless include_url is true."
                                },
                                "content": {
                                  "type": "string"
                                },
                                "markdown": {
                                  "type": "string"
                                },
                                "confidence": {
                                  "type": "number"
                                },
                                "page_width": {
                                  "type": "number"
                                },
                                "segment_id": {
                                  "type": "string"
                                },
                                "page_height": {
                                  "type": "number"
                                },
                                "page_number": {
                                  "type": "integer"
                                },
                                "segment_type": {
                                  "type": "string"
                                }
                              }
                            }
                          },
                          "chunk_length": {
                            "type": "integer"
                          }
                        }
                      },
                      "description": "Array of document chunks with detailed analysis"
                    },
                    "job_id": {
                      "type": "string",
                      "description": "Unique identifier for the parsing job"
                    },
                    "status": {
                      "enum": [
                        "Starting",
                        "AwaitingUpload",
                        "Queued",
                        "Processing",
                        "Succeeded",
                        "Failed",
                        "Cancelled"
                      ],
                      "type": "string",
                      "description": "Current job status: Starting, Processing, Succeeded, or Failed"
                    },
                    "exports": {
                      "type": "object",
                      "description": "Presigned links per export format, valid for one hour."
                    },
                    "message": {
                      "type": "string",
                      "description": "Status detail; the failure reason when Failed."
                    },
                    "metadata": {
                      "type": "object",
                      "description": "Citation metadata when xml_citation was on."
                    },
                    "file_name": {
                      "type": "string"
                    },
                    "file_type": {
                      "type": "string"
                    },
                    "created_at": {
                      "type": "string",
                      "format": "date-time",
                      "description": "Timestamp when the job was created"
                    },
                    "page_count": {
                      "type": "integer"
                    },
                    "started_at": {
                      "type": "string",
                      "format": "date-time",
                      "nullable": true,
                      "description": "Timestamp when processing started"
                    },
                    "credit_used": {
                      "type": "integer"
                    },
                    "finished_at": {
                      "type": "string",
                      "format": "date-time",
                      "nullable": true,
                      "description": "Timestamp when processing completed"
                    },
                    "total_chunks": {
                      "type": "integer",
                      "description": "Number of chunks in the document"
                    },
                    "configuration": {
                      "type": "object",
                      "description": "The options the job ran with."
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          },
          "403": {
            "description": "Forbidden — you don't have permission to access this task."
          },
          "404": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              },
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "detail": {
                      "type": "string"
                    }
                  }
                }
              }
            },
            "description": "Job not found"
          },
          "422": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "detail": {
                      "type": "array"
                    }
                  }
                }
              }
            },
            "description": "Validation error"
          },
          "429": {
            "description": "Rate limit exceeded."
          },
          "500": {
            "content": {
              "text/plain": {
                "schema": {
                  "type": "string"
                }
              }
            },
            "description": "Internal server error."
          }
        },
        "parameters": [
          {
            "in": "path",
            "name": "job_id",
            "schema": {
              "type": "string",
              "format": "uuid"
            },
            "example": "04a7a6d8-5ef7-465a-b22a-8a98e7104dd9",
            "required": true,
            "description": "Job id returned by POST /parse or POST /parse/excel."
          },
          {
            "in": "query",
            "name": "include_chunks",
            "schema": {
              "type": "boolean"
            },
            "description": "Include the chunks array. Defaults to true."
          },
          {
            "in": "query",
            "name": "base64_urls",
            "schema": {
              "type": "boolean"
            },
            "description": "Return segment images as base64 data URIs instead of presigned links. Defaults to false."
          },
          {
            "in": "query",
            "name": "output_file",
            "schema": {
              "type": "boolean"
            },
            "description": "Return a presigned link to the raw output JSON instead of inlining the chunks. Defaults to false."
          },
          {
            "in": "query",
            "name": "enhanced_table",
            "schema": {
              "type": "boolean"
            },
            "description": "Apply enhanced table post-processing when assembling the response."
          },
          {
            "in": "query",
            "name": "merge_tables",
            "schema": {
              "type": "boolean"
            },
            "description": "Return the cached cross-page merged result for a job submitted with merge_tables. Defaults to false."
          },
          {
            "in": "query",
            "name": "include_url",
            "schema": {
              "type": "boolean"
            },
            "description": "Include pdf_url, file_url, segment image links and the input file URL in the response. Defaults to false, which returns them as null."
          }
        ],
        "description": "Check the status and retrieve results of parsing jobs",
        "operationId": "get_parse_task",
        "x-zeroclick-upstream-auth": {
          "security": [
            {
              "api_key": []
            }
          ],
          "securitySchemes": {
            "api_key": {
              "in": "header",
              "name": "api-key",
              "type": "apiKey",
              "description": "API key for authentication. Send it in the `api-key` request header."
            }
          }
        },
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/content/application/json/schema/properties/total_chunks/type",
              "/responses/200/description",
              "/parameters/path/job_id/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_NhuZy9GOUeiFES-p8ND-N",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/responses/404/description",
              "/parameters/path/job_id/description",
              "/parameters/query/include_chunks/required",
              "/parameters/query/include_chunks/description",
              "/parameters/query/base64_urls/required",
              "/parameters/query/base64_urls/description",
              "/parameters/query/output_file/required",
              "/parameters/query/output_file/description",
              "/parameters/query/merge_tables/required",
              "/parameters/query/merge_tables/description",
              "/parameters/query/include_url/required",
              "/parameters/query/include_url/description",
              "/description"
            ],
            "revisionId": "sdrn_y0k53_WIaoH6uXy4qWS0v"
          },
          {
            "gaps": [
              "Missing explicit OpenAPI definition for GET /parse/{job_id} in the provided YAML block."
            ],
            "pages": [
              1,
              15,
              16
            ],
            "sourceId": "sds_5mKZ7u4EuMmqMPpkxuqwQ",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_3aXHDqzqz34z_QepzFlix"
          },
          {
            "gaps": [
              "Missing explicit response schema definition",
              "Missing authentication details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_8VSEvjmXbbPhvOOwxMOcF",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_QKAZs3PUrondGuVmzlhew"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_ID4epED8Bj_-abfUCIVTO",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/responses/404/description",
              "/parameters/path/job_id/description",
              "/parameters/query/include_chunks/required",
              "/parameters/query/include_chunks/description",
              "/parameters/query/base64_urls/required",
              "/parameters/query/base64_urls/description",
              "/parameters/query/output_file/required",
              "/parameters/query/output_file/description",
              "/parameters/query/enhanced_table/required",
              "/parameters/query/enhanced_table/description",
              "/parameters/query/merge_tables/required",
              "/parameters/query/merge_tables/description",
              "/parameters/query/include_url/required",
              "/parameters/query/include_url/description",
              "/description"
            ],
            "revisionId": "sdrn_IJi1AJBvadyK3TgkHCnE0"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/operationId"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [],
            "pages": [
              1,
              3
            ],
            "sourceId": "sds_t9ntEcaThNlHLT-QQlldu",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_vOTBsnn3yZ9S3CfIyU2oq"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_XenLvVnJsQQESm6TWWjg0",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_x2iFA9dn9FPJBr1zpKrlu"
          }
        ],
        "x-zeroclick-services": [
          "parse"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "0",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "Free",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.000000"
          }
        }
      }
    },
    "/splitter": {
      "post": {
        "summary": "Split Document",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "job_id": {
                      "type": "string",
                      "description": "Pass to GET /splitter/{job_id}."
                    },
                    "status": {
                      "type": "string",
                      "description": "processing on creation."
                    },
                    "quota_remaining": {
                      "type": "number",
                      "description": "Remaining API quota after this request"
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          }
        },
        "parameters": [],
        "description": "Creates a splitting job for a PDF given by URL, with the categories to split into (names and optional descriptions), and returns the job id at once. Every page is classified and the pages of each category go to their own PDF; categories matching no page produce no file. Poll GET /splitter/{job_id} for the files with download links and confidence scores. enable_reordering restores logical page order. Usage is the page count of the PDF.",
        "operationId": "splitDocument",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "example": {
                  "file_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
                  "categories": "[{\"name\":\"invoice\",\"description\":\"Itemised charges\"},{\"name\":\"contract\",\"description\":\"Agreements and terms\"}]"
                },
                "required": [
                  "file_url",
                  "categories"
                ],
                "properties": {
                  "file_url": {
                    "type": "string",
                    "format": "uri",
                    "description": "Public or presigned URL of the PDF to split."
                  },
                  "categories": {
                    "type": "string",
                    "items": {
                      "type": "string"
                    },
                    "description": "JSON-encoded array of category objects, each with a required name and an optional description that helps separate similar categories, for example [{\"name\":\"invoice\",\"description\":\"Itemised charges\"},{\"name\":\"contract\"}], sent as a string."
                  },
                  "enable_reordering": {
                    "type": "boolean",
                    "default": false,
                    "description": "Reorder the pages inside each output file into logical order using content and page numbers. Applies only to categories with more than one page."
                  }
                }
              }
            },
            "multipart/form-data": {
              "schema": {
                "type": "object",
                "required": [
                  "categories"
                ],
                "properties": {
                  "file": {
                    "type": "string",
                    "format": "binary",
                    "description": "PDF file to split. Either file or file_url must be provided."
                  },
                  "file_url": {
                    "type": "string",
                    "description": "URL to a PDF file to split. Either file or file_url must be provided. Example: https://example.com/mixed_documents.pdf"
                  },
                  "categories": {
                    "type": "string",
                    "description": "JSON string containing array of category objects with name and optional description. Example: [{\"name\":\"invoice\",\"description\":\"Business invoices with itemized charges\"},{\"name\":\"contract\",\"description\":\"Legal agreements and binding documents\"},{\"name\":\"report\"}]"
                  },
                  "enable_reordering": {
                    "type": "boolean",
                    "anyOf": [
                      {
                        "type": "boolean"
                      },
                      {
                        "type": "null"
                      }
                    ],
                    "title": "Enable Reordering",
                    "default": false,
                    "description": "Reorder pages within each category after classification, using content and page numbers to infer the logical order. Only applied to categories that match more than one page."
                  }
                }
              },
              "encoding": {
                "file": {
                  "contentType": "application/pdf"
                }
              }
            }
          },
          "required": true
        },
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/content/application/json/schema/properties/job_id/description",
              "/responses/200/content/application/json/schema/properties/status/description",
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_B4xwgHC4TMA6tcBIn5jBv",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description",
              "/requestBody/content/multipart/form-data/schema/properties/file_url/description",
              "/requestBody/content/multipart/form-data/schema/properties/categories/description",
              "/requestBody/content/multipart/form-data/schema/properties/enable_reordering/description"
            ],
            "revisionId": "sdrn_GbGq_O-jy0dGkXnHPkM0v"
          },
          {
            "gaps": [
              "Missing explicit schema for response body fields.",
              "Missing authentication details."
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_JF5PUQ1W1UL7xpC3A91kr",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/requestBody/content/application/json/schema/properties/file_url/description",
              "/requestBody/content/application/json/schema/properties/categories/type",
              "/requestBody/content/application/json/schema/properties/categories/description"
            ],
            "revisionId": "sdrn_rE7QXa-FnBL3IEblfZwRs"
          },
          {
            "gaps": [
              "Missing requestBody schema",
              "Missing response schema"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [
              "Missing requestBody schema details",
              "Missing response schema details"
            ],
            "pages": [
              49
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          }
        ],
        "x-zeroclick-services": [
          "split"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "20000",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "$0.020000 per page (pages, service split)",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.020000"
          },
          "rates": [
            {
              "service": "split",
              "meter": "pages",
              "unit": "page",
              "unitSize": 1,
              "priceUsd": "0.020000",
              "includedUnits": 0
            }
          ]
        }
      }
    },
    "/splitter/{job_id}": {
      "get": {
        "summary": "Get Split Status",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "error": {
                      "type": "string",
                      "nullable": true,
                      "description": "Error message if job failed"
                    },
                    "job_id": {
                      "type": "string",
                      "description": "Unique identifier for the splitting job"
                    },
                    "result": {
                      "type": "object",
                      "nullable": true,
                      "properties": {
                        "files": {
                          "type": "array",
                          "items": {
                            "type": "object",
                            "properties": {
                              "name": {
                                "type": "string",
                                "description": "Name of the split file"
                              },
                              "path": {
                                "type": "string",
                                "description": "Relative path to the file"
                              },
                              "type": {
                                "type": "string",
                                "description": "File type (always 'file')"
                              },
                              "fileId": {
                                "type": "string",
                                "description": "Unique file identifier"
                              },
                              "full_path": {
                                "type": "string",
                                "description": "Presigned download link, valid about an hour."
                              },
                              "confidence_score": {
                                "type": "number",
                                "description": "Classification confidence score (0-1)"
                              }
                            }
                          },
                          "description": "Array of split PDF files"
                        },
                        "message": {
                          "type": "string",
                          "description": "Success/failure message"
                        },
                        "success": {
                          "type": "boolean",
                          "description": "Whether splitting succeeded"
                        }
                      },
                      "description": "Split results (only present when status is completed)"
                    },
                    "status": {
                      "enum": [
                        "queued",
                        "processing",
                        "completed",
                        "failed"
                      ],
                      "type": "string",
                      "description": "Current job status (queued, processing, completed, failed)"
                    },
                    "file_url": {
                      "type": "string",
                      "description": "Presigned link to the original upload, valid about an hour."
                    },
                    "progress": {
                      "type": "string",
                      "description": "Progress message"
                    },
                    "file_name": {
                      "type": "string",
                      "description": "Name of the original file"
                    },
                    "parameters": {
                      "type": "object",
                      "properties": {
                        "classes": {
                          "type": "array",
                          "items": {
                            "type": "string"
                          },
                          "description": "List of category names"
                        },
                        "page_count": {
                          "type": "integer",
                          "description": "Number of pages in the uploaded document"
                        },
                        "enable_reordering": {
                          "type": "boolean",
                          "description": "Whether pages were reordered within each category after classification"
                        },
                        "category_descriptions": {
                          "type": "object",
                          "description": "Category descriptions map"
                        }
                      },
                      "description": "Job parameters"
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          }
        },
        "parameters": [
          {
            "in": "path",
            "name": "job_id",
            "schema": {
              "type": "string",
              "format": "uuid"
            },
            "example": "04a7a6d8-5ef7-465a-b22a-8a98e7104dd9",
            "required": true,
            "description": "Job id returned by POST /splitter."
          }
        ],
        "description": "Check the status and retrieve results of document splitting jobs",
        "operationId": "getSplitJob",
        "x-zeroclick-upstream-auth": {
          "security": [
            {
              "apiKeyAuth": []
            }
          ],
          "securitySchemes": {
            "apiKeyAuth": {
              "in": "header",
              "name": "api-key",
              "type": "apiKey"
            }
          }
        },
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/content/application/json/schema/properties/result/properties/files/items/properties/full_path/description",
              "/responses/200/content/application/json/schema/properties/file_url/description",
              "/responses/200/description",
              "/parameters/path/job_id/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [
              "Missing explicit response schema."
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_JF5PUQ1W1UL7xpC3A91kr",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_rE7QXa-FnBL3IEblfZwRs"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/operationId"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [],
            "pages": [
              1
            ],
            "sourceId": "sds_LzBx37uch8jXyEZ1ZCgTh",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/parameters/path/job_id/description"
            ],
            "revisionId": "sdrn_jG5YpyrWqyDo2NUF7fiAZ"
          },
          {
            "gaps": [
              "Missing response schema details"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/operationId"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          }
        ],
        "x-zeroclick-services": [
          "split"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "0",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "Free",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.000000"
          }
        }
      }
    },
    "/v2/extract": {
      "post": {
        "summary": "Extract Data",
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "job_id": {
                      "type": "string",
                      "nullable": true,
                      "description": "Pass to GET /extract/{job_id}. Null when status is pii_blocked."
                    },
                    "reason": {
                      "type": "string",
                      "description": "pii_detected or pii_detected:<severity> on a pii_blocked response."
                    },
                    "status": {
                      "type": "string",
                      "description": "queued on creation, or pii_blocked when the PII check stopped the job."
                    },
                    "blocked": {
                      "type": "boolean",
                      "description": "Present and true on a pii_blocked response."
                    },
                    "message": {
                      "type": "string",
                      "description": "Descriptive message about the job creation"
                    },
                    "quota_remaining": {
                      "type": "number",
                      "description": "Number of Credits remaining in your quota"
                    }
                  }
                }
              }
            },
            "description": "Successful response"
          },
          "401": {
            "description": "Agent identity credential required: register once, then retry with Authorization: Bearer <token>."
          },
          "402": {
            "description": "Payment required"
          }
        },
        "parameters": [],
        "description": "Creates an extraction job for a PDF given by URL, with a JSON Schema of the fields to pull out, and returns the job id at once. Poll GET /extract/{job_id} for the typed values, each with a confidence score and, when citations are on, the page and bounding box it came from. Model tiers trade speed for thoroughness; high_accuracy_mode adds a verification pass. Usage is the page count of the PDF.",
        "operationId": "extractData",
        "requestBody": {
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "example": {
                  "file_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
                  "schema_data": "{\"type\":\"object\",\"properties\":{\"title\":{\"type\":\"string\",\"description\":\"Document title\"}},\"required\":[\"title\"],\"additionalProperties\":false}"
                },
                "required": [
                  "file_url",
                  "schema_data"
                ],
                "properties": {
                  "mode": {
                    "enum": [
                      "basic",
                      "agentic"
                    ],
                    "type": "string",
                    "description": "Extraction mode."
                  },
                  "model": {
                    "enum": [
                      "alpha",
                      "beta",
                      "gamma",
                      "delta"
                    ],
                    "type": "string",
                    "default": "gamma",
                    "description": "Model tier: alpha fast, beta balanced, gamma thorough (recommended), delta advanced."
                  },
                  "schema": {
                    "type": "object",
                    "description": "JSON schema describing the fields to extract."
                  },
                  "file_url": {
                    "type": "string",
                    "format": "uri",
                    "description": "Public or presigned URL of the PDF to extract from."
                  },
                  "detect_pii": {
                    "type": "boolean",
                    "default": false,
                    "description": "Run a PII detection pass first. When PII at or above pii_block_severity is found the job is not created and the response says so."
                  },
                  "pii_engine": {
                    "enum": [
                      "standard",
                      "advanced"
                    ],
                    "type": "string",
                    "default": "standard",
                    "description": "PII detector: standard is the fast pattern engine, advanced has higher precision."
                  },
                  "schema_data": {
                    "type": "string",
                    "description": "The JSON Schema to extract, JSON-encoded as a string: a root object with properties, required and additionalProperties false. Field descriptions guide the model. Types string, number, integer, boolean, array, object and null are supported."
                  },
                  "schema_name": {
                    "type": "string",
                    "description": "Optional name stored with the job for traceability."
                  },
                  "enable_citations": {
                    "type": "boolean",
                    "default": false,
                    "description": "Return a citation per value with bbox as left, top, right, bottom in PDF points, the page number and the page size."
                  },
                  "high_accuracy_mode": {
                    "type": "boolean",
                    "default": false,
                    "description": "Cross-check every value against the document and re-verify uncertain fields before returning. Slower."
                  },
                  "pii_block_severity": {
                    "enum": [
                      "any",
                      "low",
                      "medium",
                      "high"
                    ],
                    "type": "string",
                    "default": "high",
                    "description": "Severity that blocks the job when detect_pii is on: any finding, quasi-identifiers (names, dates, locations), contact details (email, phone), or direct identifiers only (SSN, passport, card numbers)."
                  }
                }
              }
            },
            "multipart/form-data": {
              "schema": {
                "type": "object",
                "required": [
                  "schema_data"
                ],
                "properties": {
                  "mode": {
                    "enum": [
                      "basic",
                      "agentic"
                    ],
                    "type": "string",
                    "nullable": true,
                    "description": "Extraction mode preset: `basic` or `agentic`. A mode applies a recommended extraction configuration. Omit to use the default configuration."
                  },
                  "model": {
                    "enum": [
                      "alpha",
                      "beta",
                      "gamma",
                      "delta"
                    ],
                    "type": "string",
                    "default": "gamma",
                    "description": "Model tier to use for extraction. Options: alpha, beta, gamma (default, recommended), delta"
                  },
                  "file_url": {
                    "type": "string",
                    "description": "URL to a PDF file to process. Either pdf_file or file_url must be provided."
                  },
                  "pdf_file": {
                    "type": "string",
                    "format": "binary",
                    "description": "The PDF or image (PNG, JPEG, TIFF, WebP) to process for data extraction. Maximum file size: 500MB. Either pdf_file or file_url must be provided."
                  },
                  "detect_pii": {
                    "type": "boolean",
                    "title": "Detect Pii",
                    "default": false,
                    "description": "Run a pre-flight PII check before extraction. If PII is found, no extraction job is created and the endpoint returns HTTP 200 with \"status\": \"pii_blocked\" and \"blocked\": true in the body."
                  },
                  "pii_engine": {
                    "enum": [
                      "standard",
                      "advanced"
                    ],
                    "type": "string",
                    "default": "standard",
                    "description": "PII detection engine: 'standard' (default) or 'advanced' (higher precision)."
                  },
                  "schema_data": {
                    "type": "string",
                    "description": "JSON schema defining the structure and fields to extract from the document. Example: {\"type\":\"object\",\"properties\":{\"invoice_number\":{\"type\":\"string\",\"description\":\"The invoice number\"}},\"required\":[\"invoice_number\"],\"additionalProperties\":false}"
                  },
                  "schema_name": {
                    "type": "string",
                    "anyOf": [
                      {
                        "type": "string"
                      },
                      {
                        "type": "null"
                      }
                    ],
                    "title": "Schema Name",
                    "description": "Optional name identifying the schema, stored with the job for traceability."
                  },
                  "enable_memory": {
                    "type": "boolean",
                    "default": false,
                    "description": "Apply your organization's saved rules to the schema fields they act on. Every value a rule changed carries a memory note saying which rule changed it and what was originally extracted, and the job's `metadata.memory` lists the rules that acted and any that could not, with the reason. Requires memory to be enabled for your organization. Defaults to false."
                  },
                  "enable_citations": {
                    "type": "boolean",
                    "default": false,
                    "description": "Return bounding box coordinates for extracted values"
                  },
                  "high_accuracy_mode": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable an agentic verification and validation layer for higher accuracy/consistency."
                  },
                  "pii_block_severity": {
                    "enum": [
                      "any",
                      "low",
                      "medium",
                      "high"
                    ],
                    "type": "string",
                    "default": "high",
                    "description": "Severity threshold that blocks extraction when detect_pii is enabled: 'any', 'low', 'medium', or 'high'."
                  },
                  "enable_computed_fields": {
                    "type": "boolean",
                    "default": false,
                    "description": "Beta. Calculate fields that aren't printed on the document from other extracted fields, as described in the field's schema description. Each calculated field returns a `computed` object with its inputs and outcome."
                  }
                }
              }
            }
          },
          "required": true
        },
        "x-zeroclick-document-sources": [
          {
            "gaps": [],
            "pages": [],
            "sourceId": "sds_2RLLkcitOLCPsZ5VjJkss",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/content/application/json/schema/properties/job_id/description",
              "/responses/200/content/application/json/schema/properties/status/description",
              "/description"
            ],
            "revisionId": "sdrn_UkEQmMgQM00ckAymuzj1Z"
          },
          {
            "gaps": [],
            "pages": [
              1,
              2,
              3,
              4,
              5,
              6,
              7,
              8,
              9,
              10,
              11,
              12,
              13,
              14,
              15,
              16,
              17,
              18,
              19,
              20
            ],
            "sourceId": "sds_kaK4CHFpMuf2E4eiG8lYb",
            "authority": "supplemental",
            "conflicts": [
              "/description",
              "/requestBody/content/multipart/form-data/schema/properties/pdf_file/description",
              "/requestBody/content/multipart/form-data/schema/properties/detect_pii/description",
              "/requestBody/content/multipart/form-data/schema/properties/schema_data/description",
              "/requestBody/content/multipart/form-data/schema/properties/enable_computed_fields/description"
            ],
            "revisionId": "sdrn_1-Xtdh3_uFZoAztsI3pVM"
          },
          {
            "gaps": [
              "Missing requestBody schema",
              "Missing response schema"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_LANLzm6vZzlEgKmkJH8vw",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description"
            ],
            "revisionId": "sdrn_brdLRNhkaEQ3r8peasVCP"
          },
          {
            "gaps": [
              "Missing document input field definition (e.g., file upload or URL)",
              "Missing response schema definition"
            ],
            "pages": [
              1
            ],
            "sourceId": "sds_PU27fDDP3LB5OhJvMLyZR",
            "authority": "supplemental",
            "conflicts": [
              "/summary",
              "/responses/200/description",
              "/description",
              "/requestBody/content/application/json/schema/required"
            ],
            "revisionId": "sdrn_w2fTIvoK5jWbYDkSqqvLs"
          },
          {
            "gaps": [
              "Missing requestBody schema details",
              "Missing response schema details"
            ],
            "pages": [
              45
            ],
            "sourceId": "sds_u2y5tQsQIFA962B-LGhvM",
            "authority": "supplemental",
            "conflicts": [
              "/responses/200/description",
              "/description"
            ],
            "revisionId": "sdrn_RoclWh9dCY2TIwLPvjooz"
          }
        ],
        "x-zeroclick-services": [
          "extract"
        ],
        "x-payment-info": {
          "access": "payg",
          "protocols": [
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            },
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            }
          ],
          "offers": [
            {
              "amount": "20000",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "description": "$0.020000 per page (pages, service extract)",
              "intent": "charge",
              "method": "tempo"
            }
          ],
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0.020000"
          },
          "rates": [
            {
              "service": "extract",
              "meter": "pages",
              "unit": "page",
              "unitSize": 1,
              "priceUsd": "0.020000",
              "includedUnits": 0
            }
          ]
        }
      }
    },
    "/zeroclick/agent/quote": {
      "post": {
        "operationId": "sellerAgentQuote",
        "summary": "Get a free seller API quote and purchase guide",
        "description": "Describe your task to get the matching API contract, prices, prerequisites and next steps. This is a $0 wallet-proof lookup, not the seller's paid service. No purchase is executed. Without a wallet, use /zeroclick/agent/guide.",
        "servers": [
          {
            "url": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn"
          }
        ],
        "security": [
          {
            "sellerAgentX402": []
          },
          {
            "sellerAgentMpp": []
          }
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$schema": "https://json-schema.org/draft/2020-12/schema",
                "type": "object",
                "properties": {
                  "goal": {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 2000,
                    "description": "Describe the task and known inputs. Do not include credentials."
                  },
                  "quantity": {
                    "description": "Number of API calls, not returned items. Omit when unknown; describe desired output in goal.",
                    "type": "integer",
                    "minimum": 1,
                    "maximum": 1000000
                  },
                  "budgetUsd": {
                    "description": "Total cash budget in USD. A quote does not authorize spending.",
                    "type": "string",
                    "pattern": "^(0|[1-9]\\d{0,8})(\\.\\d{1,6})?$"
                  },
                  "budgetExclusive": {
                    "type": "boolean"
                  },
                  "reviewAfterCalls": {
                    "type": "integer",
                    "minimum": 1,
                    "maximum": 1000000
                  },
                  "requirements": {
                    "type": "string",
                    "minLength": 1,
                    "maxLength": 300
                  },
                  "humanAvailable": {
                    "description": "Whether a human is in the loop; omit when unknown. Executing a human's request without further interruptions does not by itself mean false.",
                    "type": "boolean"
                  },
                  "payment": {
                    "description": "Known payment method for the eventual purchase, independent of this free lookup's wallet proof.",
                    "type": "string",
                    "enum": [
                      "x402",
                      "mpp",
                      "card"
                    ]
                  }
                },
                "required": [
                  "goal"
                ],
                "additionalProperties": false
              },
              "example": {
                "goal": "Find the available services, prices and purchase steps"
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Task guidance; inspect status before executing anything",
            "content": {
              "application/json": {
                "schema": {
                  "$schema": "https://json-schema.org/draft/2020-12/schema",
                  "type": "object",
                  "properties": {
                    "status": {
                      "type": "string",
                      "enum": [
                        "quoted",
                        "catalog",
                        "ready",
                        "needs_input",
                        "blocked",
                        "unknown",
                        "unsupported",
                        "unavailable"
                      ]
                    },
                    "priceUsd": {
                      "type": "string",
                      "const": "0"
                    },
                    "guide": {
                      "type": "string",
                      "description": "Markdown guidance containing the task result, exact contract, pricing and next steps when available. No purchase is executed."
                    },
                    "guideUrl": {
                      "type": "string",
                      "format": "uri",
                      "description": "Wallet-free advisor endpoint for further planning or recovery."
                    }
                  },
                  "required": [
                    "status",
                    "priceUsd",
                    "guide",
                    "guideUrl"
                  ],
                  "additionalProperties": false
                }
              }
            }
          },
          "402": {
            "description": "$0 x402 or MPP wallet proof required; sign and retry the same request. No funds are transferred."
          },
          "503": {
            "description": "Advisor unavailable; use the wallet-free guide or direct storefront references"
          }
        },
        "x-payment-info": {
          "access": "payg",
          "price": {
            "mode": "fixed",
            "currency": "USD",
            "amount": "0"
          },
          "protocols": [
            {
              "x402": {
                "network": "eip155:8453",
                "scheme": "exact",
                "currency": "USDC"
              }
            },
            {
              "mpp": {
                "method": "tempo",
                "intent": "charge",
                "currency": "USD"
              }
            }
          ],
          "offers": [
            {
              "amount": "0",
              "currency": "0x20C000000000000000000000b9537d11c60E8b50",
              "method": "tempo",
              "intent": "charge",
              "description": "Free seller advisor lookup"
            }
          ]
        }
      }
    }
  },
  "x-zeroclick-navigation-footer": {
    "instructions": [
      "Use this spec if it contains the operation and details you need. Otherwise, search or open a relevant service spec using the links below.",
      "Find service slugs in x-zeroclick-services or x-payment-info.rates[].service; use them in serviceSpecTemplate, never as request values.",
      "URL-encode template values. Search is ranked; service, path, and method filters are exact. Filters combine.",
      "Pages contain up to 10 operations; follow info.x-next or the Link header if you need more results. Shared operations retain all selector values."
    ],
    "fullSpec": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json",
    "services": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services",
    "serviceSpecTemplate": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/services/{slug}/openapi.json",
    "searchTemplate": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json?q={text}",
    "operationTemplate": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json?path={path}&method={method}",
    "firstPage": "https://agents.unsiloed.ai/zcj/1a7cfxixd2kn/openapi.json?page=1"
  }
}
