{ "openapi": "3.0.3", "info": { "title": "AnyToMarkdown - PDF to Markdown and Document Parser API", "version": "1.0.0", "description": "**PDF to Markdown, Word to Markdown, URL to Markdown:** turn **any document or web page into clean, LLM-ready Markdown** - plus RAG-ready chunks and exact token counts - with one API call.\n\n**Inputs:** PDF (with OCR for scans), Word (DOCX/DOC), PowerPoint (PPTX/PPT), Excel (XLSX/XLS/XLSB), CSV/TSV, HTML & any public URL, EPUB, e-mails (EML/MSG with attachments), RTF, OpenDocument (ODT/ODS/ODP), Jupyter notebooks, subtitles (SRT/VTT), JSON/XML/Markdown/code, ZIP archives and images.\n\n**What you get:** headings, nested lists, tables (including PDF tables), links, footnotes, code blocks and metadata - without headers, footers or page numbers. Optional per-page output, structure-aware chunks with heading breadcrumbs and page numbers, and OpenAI-compatible token counts (o200k_base / cl100k_base).\n\n**AI agents:** the same features are available as MCP tools at `/mcp` (Claude Code, Cursor, VS Code, n8n AI agents...).\n\n**Privacy:** files are processed in memory and never stored." }, "servers": [ { "url": "https://anymarkdownapi.gtgroup.dev" } ], "tags": [ { "name": "Convert", "description": "Convert files and URLs to Markdown / text" }, { "name": "RAG utilities", "description": "Chunking and token counting" }, { "name": "AI agents (MCP)", "description": "Use the API as tools from Claude, Cursor and other MCP clients" }, { "name": "Info", "description": "Supported formats and your plan limits" } ], "paths": { "/v1/convert": { "post": { "tags": [ "Convert" ], "operationId": "convertDocument", "summary": "Convert PDF, Word, Excel or PowerPoint file to Markdown", "description": "Upload a file (multipart `file`), post raw bytes, or send JSON with `url` / `base64`. Returns Markdown plus metadata, and optionally per-page content and RAG chunks.", "parameters": [ { "$ref": "#/components/parameters/FileName" }, { "$ref": "#/components/parameters/OutputFormat" }, { "$ref": "#/components/parameters/Pages" }, { "$ref": "#/components/parameters/Ocr" }, { "$ref": "#/components/parameters/OcrLanguages" }, { "$ref": "#/components/parameters/MainContentOnly" }, { "$ref": "#/components/parameters/IncludeImages" }, { "$ref": "#/components/parameters/IncludeLinks" }, { "$ref": "#/components/parameters/PageMarkers" }, { "$ref": "#/components/parameters/IncludeHeadersFooters" }, { "$ref": "#/components/parameters/IncludeSpeakerNotes" }, { "$ref": "#/components/parameters/ConvertAttachments" }, { "$ref": "#/components/parameters/Password" }, { "$ref": "#/components/parameters/IncludePages" }, { "$ref": "#/components/parameters/IncludeChunks" }, { "$ref": "#/components/parameters/IncludeContent" }, { "$ref": "#/components/parameters/ChunkSize" }, { "$ref": "#/components/parameters/ChunkOverlap" }, { "$ref": "#/components/parameters/Tokenizer" }, { "$ref": "#/components/parameters/MaxRowsPerSheet" } ], "requestBody": { "required": false, "description": "Send the document in one of three ways: **multipart/form-data** with a `file` field, a **JSON** body with `url` or `base64`, or the **raw file bytes** as the body (any content type).", "content": { "multipart/form-data": { "schema": { "type": "object", "required": [ "file" ], "properties": { "file": { "type": "string", "format": "binary", "description": "The document to convert (PDF, DOCX, DOC, PPTX, PPT, XLSX, XLS, CSV, HTML, EPUB, EML, MSG, RTF, ODT, ODS, ODP, IPYNB, SRT, VTT, TXT, MD, JSON, XML, ZIP, images)." }, "fileName": { "type": "string", "description": "Override the file name used for format detection." }, "outputFormat": { "type": "string", "enum": [ "markdown", "text" ], "default": "markdown" }, "pages": { "type": "string", "example": "1-10" }, "ocr": { "type": "string", "enum": [ "auto", "force", "off" ], "default": "auto" }, "ocrLanguages": { "type": "string", "default": "eng" }, "mainContentOnly": { "type": "boolean" }, "includeImages": { "type": "boolean", "default": true }, "includeLinks": { "type": "boolean", "default": true }, "pageMarkers": { "type": "boolean", "default": false }, "includeHeadersFooters": { "type": "boolean", "default": false }, "includeSpeakerNotes": { "type": "boolean", "default": true }, "convertAttachments": { "type": "boolean", "default": true }, "password": { "type": "string" }, "includePages": { "type": "boolean", "default": false }, "includeChunks": { "type": "boolean", "default": false }, "includeContent": { "type": "boolean", "default": true }, "chunkSize": { "type": "integer", "minimum": 64, "maximum": 8192, "default": 512 }, "chunkOverlap": { "type": "integer", "minimum": 0, "default": 64 }, "tokenizer": { "type": "string", "enum": [ "o200k_base", "cl100k_base" ], "default": "o200k_base" }, "maxRowsPerSheet": { "type": "integer", "minimum": 1 } } } }, "application/json": { "schema": { "type": "object", "description": "Provide exactly one of `url` or `base64`. All conversion options can be given here or as query parameters.", "properties": { "url": { "type": "string", "format": "uri", "description": "Public URL of a page or document.", "example": "https://arxiv.org/pdf/1706.03762" }, "base64": { "type": "string", "description": "File content, base64 encoded (a `data:...;base64,` prefix is accepted)." }, "fileName": { "type": "string", "description": "Original file name (hint for format detection).", "example": "invoice.pdf" }, "outputFormat": { "type": "string", "enum": [ "markdown", "text" ], "default": "markdown" }, "pages": { "type": "string", "example": "1-10" }, "ocr": { "type": "string", "enum": [ "auto", "force", "off" ], "default": "auto" }, "ocrLanguages": { "type": "string", "default": "eng" }, "mainContentOnly": { "type": "boolean" }, "includeImages": { "type": "boolean", "default": true }, "includeLinks": { "type": "boolean", "default": true }, "pageMarkers": { "type": "boolean", "default": false }, "includeHeadersFooters": { "type": "boolean", "default": false }, "includeSpeakerNotes": { "type": "boolean", "default": true }, "convertAttachments": { "type": "boolean", "default": true }, "password": { "type": "string" }, "includePages": { "type": "boolean", "default": false }, "includeChunks": { "type": "boolean", "default": false }, "includeContent": { "type": "boolean", "default": true }, "chunkSize": { "type": "integer", "minimum": 64, "maximum": 8192, "default": 512 }, "chunkOverlap": { "type": "integer", "minimum": 0, "default": 64 }, "tokenizer": { "type": "string", "enum": [ "o200k_base", "cl100k_base" ], "default": "o200k_base" }, "maxRowsPerSheet": { "type": "integer", "minimum": 1 } }, "example": { "url": "https://arxiv.org/pdf/1706.03762", "pages": "1-3", "includeChunks": true, "chunkSize": 512 } } }, "application/octet-stream": { "schema": { "type": "string", "format": "binary" } } } }, "responses": { "200": { "description": "Converted document.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ConvertResponse" } } } }, "400": { "description": "Invalid request (bad option values, missing input, blocked or invalid URL).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "invalid_request", "message": "'chunkSize' must be between 64 and 8192 tokens." } } } } }, "401": { "description": "Missing or invalid credentials.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "413": { "description": "File larger than your plan allows.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "file_too_large", "message": "Input exceeds the maximum size of 10 MB for your plan." } } } } }, "415": { "description": "Unsupported or unrecognized format.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "422": { "description": "The document could not be converted (corrupt file, password required, URL fetch failed...).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "password_required", "message": "This PDF is password protected. Pass the password in the 'password' parameter." } } } } }, "429": { "description": "Too many simultaneous requests for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "Server busy; retry after a few seconds.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "504": { "description": "Conversion did not finish within your plan's time limit.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } }, "get": { "tags": [ "Convert" ], "operationId": "convertUrl", "summary": "Convert web page or online document URL to Markdown", "description": "Fetches the URL (web page or file) and converts it. Web pages are reduced to their main content by default.", "parameters": [ { "name": "url", "in": "query", "required": true, "description": "Public URL of a web page or document (PDF, DOCX, XLSX...). Google Docs/Sheets/Slides, Google Drive, Dropbox and GitHub share links are converted to direct downloads automatically.", "schema": { "type": "string", "format": "uri" }, "example": "https://en.wikipedia.org/wiki/Markdown" }, { "$ref": "#/components/parameters/FileName" }, { "$ref": "#/components/parameters/OutputFormat" }, { "$ref": "#/components/parameters/Pages" }, { "$ref": "#/components/parameters/Ocr" }, { "$ref": "#/components/parameters/OcrLanguages" }, { "$ref": "#/components/parameters/MainContentOnly" }, { "$ref": "#/components/parameters/IncludeImages" }, { "$ref": "#/components/parameters/IncludeLinks" }, { "$ref": "#/components/parameters/PageMarkers" }, { "$ref": "#/components/parameters/IncludeHeadersFooters" }, { "$ref": "#/components/parameters/IncludeSpeakerNotes" }, { "$ref": "#/components/parameters/ConvertAttachments" }, { "$ref": "#/components/parameters/Password" }, { "$ref": "#/components/parameters/IncludePages" }, { "$ref": "#/components/parameters/IncludeChunks" }, { "$ref": "#/components/parameters/IncludeContent" }, { "$ref": "#/components/parameters/ChunkSize" }, { "$ref": "#/components/parameters/ChunkOverlap" }, { "$ref": "#/components/parameters/Tokenizer" }, { "$ref": "#/components/parameters/MaxRowsPerSheet" } ], "responses": { "200": { "description": "Converted document.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ConvertResponse" } } } }, "400": { "description": "Invalid request (bad option values, missing input, blocked or invalid URL).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "invalid_request", "message": "'chunkSize' must be between 64 and 8192 tokens." } } } } }, "401": { "description": "Missing or invalid credentials.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "413": { "description": "File larger than your plan allows.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "file_too_large", "message": "Input exceeds the maximum size of 10 MB for your plan." } } } } }, "415": { "description": "Unsupported or unrecognized format.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "422": { "description": "The document could not be converted (corrupt file, password required, URL fetch failed...).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "password_required", "message": "This PDF is password protected. Pass the password in the 'password' parameter." } } } } }, "429": { "description": "Too many simultaneous requests for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "Server busy; retry after a few seconds.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "504": { "description": "Conversion did not finish within your plan's time limit.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } }, "/v1/convert/raw": { "post": { "tags": [ "Convert" ], "operationId": "convertDocumentRaw", "summary": "Convert file to Markdown (plain text response)", "description": "Same input as `POST /v1/convert`, but the response body is the Markdown (`text/markdown`) or text itself. Handy for no-code tools and AI agents. Stats are returned in `X-Token-Count`, `X-Pages-Processed`, `X-Source-Format`, `X-Truncated` headers.", "parameters": [ { "$ref": "#/components/parameters/FileName" }, { "$ref": "#/components/parameters/OutputFormat" }, { "$ref": "#/components/parameters/Pages" }, { "$ref": "#/components/parameters/Ocr" }, { "$ref": "#/components/parameters/OcrLanguages" }, { "$ref": "#/components/parameters/MainContentOnly" }, { "$ref": "#/components/parameters/IncludeImages" }, { "$ref": "#/components/parameters/IncludeLinks" }, { "$ref": "#/components/parameters/PageMarkers" }, { "$ref": "#/components/parameters/IncludeHeadersFooters" }, { "$ref": "#/components/parameters/IncludeSpeakerNotes" }, { "$ref": "#/components/parameters/ConvertAttachments" }, { "$ref": "#/components/parameters/Password" }, { "$ref": "#/components/parameters/IncludePages" }, { "$ref": "#/components/parameters/IncludeChunks" }, { "$ref": "#/components/parameters/IncludeContent" }, { "$ref": "#/components/parameters/ChunkSize" }, { "$ref": "#/components/parameters/ChunkOverlap" }, { "$ref": "#/components/parameters/Tokenizer" }, { "$ref": "#/components/parameters/MaxRowsPerSheet" } ], "requestBody": { "required": false, "description": "Send the document in one of three ways: **multipart/form-data** with a `file` field, a **JSON** body with `url` or `base64`, or the **raw file bytes** as the body (any content type).", "content": { "multipart/form-data": { "schema": { "type": "object", "required": [ "file" ], "properties": { "file": { "type": "string", "format": "binary", "description": "The document to convert (PDF, DOCX, DOC, PPTX, PPT, XLSX, XLS, CSV, HTML, EPUB, EML, MSG, RTF, ODT, ODS, ODP, IPYNB, SRT, VTT, TXT, MD, JSON, XML, ZIP, images)." }, "fileName": { "type": "string", "description": "Override the file name used for format detection." }, "outputFormat": { "type": "string", "enum": [ "markdown", "text" ], "default": "markdown" }, "pages": { "type": "string", "example": "1-10" }, "ocr": { "type": "string", "enum": [ "auto", "force", "off" ], "default": "auto" }, "ocrLanguages": { "type": "string", "default": "eng" }, "mainContentOnly": { "type": "boolean" }, "includeImages": { "type": "boolean", "default": true }, "includeLinks": { "type": "boolean", "default": true }, "pageMarkers": { "type": "boolean", "default": false }, "includeHeadersFooters": { "type": "boolean", "default": false }, "includeSpeakerNotes": { "type": "boolean", "default": true }, "convertAttachments": { "type": "boolean", "default": true }, "password": { "type": "string" }, "includePages": { "type": "boolean", "default": false }, "includeChunks": { "type": "boolean", "default": false }, "includeContent": { "type": "boolean", "default": true }, "chunkSize": { "type": "integer", "minimum": 64, "maximum": 8192, "default": 512 }, "chunkOverlap": { "type": "integer", "minimum": 0, "default": 64 }, "tokenizer": { "type": "string", "enum": [ "o200k_base", "cl100k_base" ], "default": "o200k_base" }, "maxRowsPerSheet": { "type": "integer", "minimum": 1 } } } }, "application/json": { "schema": { "type": "object", "description": "Provide exactly one of `url` or `base64`. All conversion options can be given here or as query parameters.", "properties": { "url": { "type": "string", "format": "uri", "description": "Public URL of a page or document.", "example": "https://arxiv.org/pdf/1706.03762" }, "base64": { "type": "string", "description": "File content, base64 encoded (a `data:...;base64,` prefix is accepted)." }, "fileName": { "type": "string", "description": "Original file name (hint for format detection).", "example": "invoice.pdf" }, "outputFormat": { "type": "string", "enum": [ "markdown", "text" ], "default": "markdown" }, "pages": { "type": "string", "example": "1-10" }, "ocr": { "type": "string", "enum": [ "auto", "force", "off" ], "default": "auto" }, "ocrLanguages": { "type": "string", "default": "eng" }, "mainContentOnly": { "type": "boolean" }, "includeImages": { "type": "boolean", "default": true }, "includeLinks": { "type": "boolean", "default": true }, "pageMarkers": { "type": "boolean", "default": false }, "includeHeadersFooters": { "type": "boolean", "default": false }, "includeSpeakerNotes": { "type": "boolean", "default": true }, "convertAttachments": { "type": "boolean", "default": true }, "password": { "type": "string" }, "includePages": { "type": "boolean", "default": false }, "includeChunks": { "type": "boolean", "default": false }, "includeContent": { "type": "boolean", "default": true }, "chunkSize": { "type": "integer", "minimum": 64, "maximum": 8192, "default": 512 }, "chunkOverlap": { "type": "integer", "minimum": 0, "default": 64 }, "tokenizer": { "type": "string", "enum": [ "o200k_base", "cl100k_base" ], "default": "o200k_base" }, "maxRowsPerSheet": { "type": "integer", "minimum": 1 } }, "example": { "url": "https://arxiv.org/pdf/1706.03762", "pages": "1-3", "includeChunks": true, "chunkSize": 512 } } }, "application/octet-stream": { "schema": { "type": "string", "format": "binary" } } } }, "responses": { "200": { "description": "The converted content.", "content": { "text/markdown": { "schema": { "type": "string" }, "example": "# Title\n\nFirst paragraph..." }, "text/plain": { "schema": { "type": "string" } } } }, "400": { "description": "Invalid request (bad option values, missing input, blocked or invalid URL).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "invalid_request", "message": "'chunkSize' must be between 64 and 8192 tokens." } } } } }, "401": { "description": "Missing or invalid credentials.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "413": { "description": "File larger than your plan allows.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "file_too_large", "message": "Input exceeds the maximum size of 10 MB for your plan." } } } } }, "415": { "description": "Unsupported or unrecognized format.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "422": { "description": "The document could not be converted (corrupt file, password required, URL fetch failed...).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "password_required", "message": "This PDF is password protected. Pass the password in the 'password' parameter." } } } } }, "429": { "description": "Too many simultaneous requests for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "Server busy; retry after a few seconds.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "504": { "description": "Conversion did not finish within your plan's time limit.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } }, "get": { "tags": [ "Convert" ], "operationId": "convertUrlRaw", "summary": "Convert URL to Markdown (plain text response)", "parameters": [ { "name": "url", "in": "query", "required": true, "description": "Public URL of a web page or document (PDF, DOCX, XLSX...). Google Docs/Sheets/Slides, Google Drive, Dropbox and GitHub share links are converted to direct downloads automatically.", "schema": { "type": "string", "format": "uri" }, "example": "https://en.wikipedia.org/wiki/Markdown" }, { "$ref": "#/components/parameters/FileName" }, { "$ref": "#/components/parameters/OutputFormat" }, { "$ref": "#/components/parameters/Pages" }, { "$ref": "#/components/parameters/Ocr" }, { "$ref": "#/components/parameters/OcrLanguages" }, { "$ref": "#/components/parameters/MainContentOnly" }, { "$ref": "#/components/parameters/IncludeImages" }, { "$ref": "#/components/parameters/IncludeLinks" }, { "$ref": "#/components/parameters/PageMarkers" }, { "$ref": "#/components/parameters/IncludeHeadersFooters" }, { "$ref": "#/components/parameters/IncludeSpeakerNotes" }, { "$ref": "#/components/parameters/ConvertAttachments" }, { "$ref": "#/components/parameters/Password" }, { "$ref": "#/components/parameters/IncludePages" }, { "$ref": "#/components/parameters/IncludeChunks" }, { "$ref": "#/components/parameters/IncludeContent" }, { "$ref": "#/components/parameters/ChunkSize" }, { "$ref": "#/components/parameters/ChunkOverlap" }, { "$ref": "#/components/parameters/Tokenizer" }, { "$ref": "#/components/parameters/MaxRowsPerSheet" } ], "responses": { "200": { "description": "The converted content.", "content": { "text/markdown": { "schema": { "type": "string" } }, "text/plain": { "schema": { "type": "string" } } } }, "400": { "description": "Invalid request (bad option values, missing input, blocked or invalid URL).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "invalid_request", "message": "'chunkSize' must be between 64 and 8192 tokens." } } } } }, "401": { "description": "Missing or invalid credentials.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "413": { "description": "File larger than your plan allows.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "file_too_large", "message": "Input exceeds the maximum size of 10 MB for your plan." } } } } }, "415": { "description": "Unsupported or unrecognized format.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "422": { "description": "The document could not be converted (corrupt file, password required, URL fetch failed...).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "password_required", "message": "This PDF is password protected. Pass the password in the 'password' parameter." } } } } }, "429": { "description": "Too many simultaneous requests for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "503": { "description": "Server busy; retry after a few seconds.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "504": { "description": "Conversion did not finish within your plan's time limit.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } }, "/v1/chunk": { "post": { "tags": [ "RAG utilities" ], "operationId": "chunkText", "summary": "Split Markdown into RAG chunks", "description": "Heading-aware chunking with token budget, overlap, intact tables and code blocks, and heading breadcrumbs.", "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ChunkRequest" } } } }, "responses": { "200": { "description": "Chunks.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ChunkResponse" } } } }, "400": { "description": "Invalid request (bad option values, missing input, blocked or invalid URL).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "invalid_request", "message": "'chunkSize' must be between 64 and 8192 tokens." } } } } }, "401": { "description": "Missing or invalid credentials.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "429": { "description": "Too many simultaneous requests for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } }, "/v1/tokens": { "post": { "tags": [ "RAG utilities" ], "operationId": "countTokens", "summary": "Count GPT tokens in text", "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TokenRequest" } } } }, "responses": { "200": { "description": "Token count.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TokenResponse" } } } }, "400": { "description": "Invalid request (bad option values, missing input, blocked or invalid URL).", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" }, "example": { "success": false, "requestId": "4f1c2a9b8e7d6c5b", "error": { "code": "invalid_request", "message": "'chunkSize' must be between 64 and 8192 tokens." } } } } }, "401": { "description": "Missing or invalid credentials.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } }, "/mcp": { "post": { "tags": [ "AI agents (MCP)" ], "operationId": "mcp", "summary": "MCP server for AI agents (convert, chunk, count tokens)", "description": "Stateless MCP (Streamable HTTP) server exposing the tools `convert_url`, `convert_file`, `chunk_text` and `count_tokens`. Point Claude Code, Cursor, VS Code, n8n AI agents or any MCP client at this URL with your RapidAPI headers. Send JSON-RPC 2.0 messages with `Accept: application/json, text/event-stream`.", "parameters": [ { "name": "Accept", "in": "header", "required": true, "schema": { "type": "string", "default": "application/json, text/event-stream" } } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "description": "JSON-RPC 2.0 request", "properties": { "jsonrpc": { "type": "string", "example": "2.0" }, "id": { "type": "integer", "example": 1 }, "method": { "type": "string", "example": "tools/call" }, "params": { "type": "object" } } }, "example": { "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "convert_url", "arguments": { "url": "https://en.wikipedia.org/wiki/Markdown" } } } } } }, "responses": { "200": { "description": "JSON-RPC response (as a single server-sent event).", "content": { "text/event-stream": { "schema": { "type": "string" } }, "application/json": { "schema": { "type": "object" } } } }, "401": { "description": "Missing or invalid credentials.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "429": { "description": "Too many simultaneous requests for your account.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } } } }, "/v1/formats": { "get": { "tags": [ "Info" ], "operationId": "listFormats", "summary": "List supported formats, OCR languages and plan limits", "responses": { "200": { "description": "Formats and limits.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/FormatsResponse" } } } } } } } }, "components": { "parameters": { "OutputFormat": { "name": "outputFormat", "in": "query", "required": false, "description": "Format of `content`: GitHub-flavored **markdown** (headings, lists, tables, links) or clean plain **text**.", "schema": { "type": "string", "enum": [ "markdown", "text" ], "default": "markdown" }, "example": "markdown" }, "Pages": { "name": "pages", "in": "query", "required": false, "description": "Pages / slides / sheets / archive files to convert, e.g. `1-5,8,10-`. Default: all (up to your plan's page limit).", "schema": { "type": "string" }, "example": "1-10" }, "Ocr": { "name": "ocr", "in": "query", "required": false, "description": "OCR for scanned PDFs and images. `auto` OCRs only pages without a usable text layer; `force` OCRs every page; `off` disables OCR.", "schema": { "type": "string", "enum": [ "auto", "force", "off" ], "default": "auto" }, "example": "auto" }, "OcrLanguages": { "name": "ocrLanguages", "in": "query", "required": false, "description": "Tesseract language codes joined with `+`, e.g. `eng`, `deu`, `eng+fra`. See `GET /v1/formats` for installed languages.", "schema": { "type": "string", "default": "eng" }, "example": "eng" }, "MainContentOnly": { "name": "mainContentOnly", "in": "query", "required": false, "description": "HTML / web pages only: keep just the main article (drops navigation, ads, cookie banners, footers). Default: `true` for `url` input, `false` for uploaded HTML.", "schema": { "type": "boolean" }, "example": true }, "IncludeImages": { "name": "includeImages", "in": "query", "required": false, "description": "Emit image references (`![alt](src)`) for images that have alt text or a URL.", "schema": { "type": "boolean", "default": true }, "example": true }, "IncludeLinks": { "name": "includeLinks", "in": "query", "required": false, "description": "Keep hyperlinks. Set `false` to output link text only (saves tokens).", "schema": { "type": "boolean", "default": true }, "example": true }, "PageMarkers": { "name": "pageMarkers", "in": "query", "required": false, "description": "Insert `` markers between pages / slides / sheets.", "schema": { "type": "boolean", "default": false }, "example": false }, "IncludeHeadersFooters": { "name": "includeHeadersFooters", "in": "query", "required": false, "description": "Keep running page headers, footers and page numbers (PDF) and Word header/footer parts. Removed by default.", "schema": { "type": "boolean", "default": false }, "example": false }, "IncludeSpeakerNotes": { "name": "includeSpeakerNotes", "in": "query", "required": false, "description": "PowerPoint / ODP: include speaker notes under each slide.", "schema": { "type": "boolean", "default": true }, "example": true }, "ConvertAttachments": { "name": "convertAttachments", "in": "query", "required": false, "description": "E-mails (EML/MSG): also convert attached documents (PDF, DOCX, XLSX...) and append them.", "schema": { "type": "boolean", "default": true }, "example": true }, "Password": { "name": "password", "in": "query", "required": false, "description": "Password for encrypted PDFs or Excel workbooks.", "schema": { "type": "string" } }, "IncludePages": { "name": "includePages", "in": "query", "required": false, "description": "Also return `pages[]`: the content split per page / slide / sheet (great for citations).", "schema": { "type": "boolean", "default": false }, "example": false }, "IncludeChunks": { "name": "includeChunks", "in": "query", "required": false, "description": "Also return `chunks[]`: RAG-ready chunks that respect headings, keep tables/code intact, repeat table headers, and carry heading breadcrumbs and page numbers.", "schema": { "type": "boolean", "default": false }, "example": true }, "IncludeContent": { "name": "includeContent", "in": "query", "required": false, "description": "Set `false` to omit the full `content` (e.g. when you only need chunks).", "schema": { "type": "boolean", "default": true }, "example": true }, "ChunkSize": { "name": "chunkSize", "in": "query", "required": false, "description": "Maximum tokens per chunk.", "schema": { "type": "integer", "minimum": 64, "maximum": 8192, "default": 512 }, "example": 512 }, "ChunkOverlap": { "name": "chunkOverlap", "in": "query", "required": false, "description": "Tokens repeated from the end of the previous chunk when a section is split (max half of chunkSize).", "schema": { "type": "integer", "minimum": 0, "maximum": 4096, "default": 64 }, "example": 64 }, "Tokenizer": { "name": "tokenizer", "in": "query", "required": false, "description": "Tokenizer for token counts and chunk sizes. `o200k_base` = GPT-4o / GPT-4.1 / GPT-5 family, `cl100k_base` = GPT-4 / GPT-3.5 / OpenAI embeddings.", "schema": { "type": "string", "enum": [ "o200k_base", "cl100k_base" ], "default": "o200k_base" }, "example": "o200k_base" }, "MaxRowsPerSheet": { "name": "maxRowsPerSheet", "in": "query", "required": false, "description": "Spreadsheets/CSV: maximum rows per sheet (capped by your plan).", "schema": { "type": "integer", "minimum": 1 }, "example": 1000 }, "FileName": { "name": "fileName", "in": "query", "required": false, "description": "Original file name. Optional: the format is detected from the content, the name is only a hint (useful for raw/base64 uploads of text formats such as .csv or .md).", "schema": { "type": "string" }, "example": "report.pdf" } }, "schemas": { "SourceInfo": { "type": "object", "properties": { "type": { "type": "string", "enum": [ "upload", "binary", "base64", "url" ] }, "fileName": { "type": "string", "nullable": true }, "url": { "type": "string", "nullable": true }, "finalUrl": { "type": "string", "nullable": true, "description": "URL after redirects / share-link rewriting." }, "format": { "type": "string", "description": "Detected format id, e.g. pdf, docx, xlsx, html, code:python." }, "mimeType": { "type": "string" }, "sizeBytes": { "type": "integer", "format": "int64" } } }, "Metadata": { "type": "object", "description": "Document metadata (only known fields are returned).", "properties": { "title": { "type": "string", "nullable": true }, "author": { "type": "string", "nullable": true }, "subject": { "type": "string", "nullable": true }, "description": { "type": "string", "nullable": true }, "keywords": { "type": "string", "nullable": true }, "language": { "type": "string", "nullable": true }, "creator": { "type": "string", "nullable": true }, "producer": { "type": "string", "nullable": true }, "siteName": { "type": "string", "nullable": true }, "url": { "type": "string", "nullable": true }, "canonicalUrl": { "type": "string", "nullable": true }, "image": { "type": "string", "nullable": true }, "created": { "type": "string", "format": "date-time", "nullable": true }, "modified": { "type": "string", "format": "date-time", "nullable": true }, "published": { "type": "string", "format": "date-time", "nullable": true }, "pageCount": { "type": "integer", "nullable": true, "description": "Total pages / slides / sheets / chapters in the source." }, "extra": { "type": "object", "additionalProperties": { "type": "string" }, "nullable": true } } }, "Page": { "type": "object", "properties": { "page": { "type": "integer" }, "label": { "type": "string", "example": "Page 3" }, "content": { "type": "string" }, "tokens": { "type": "integer" } } }, "Chunk": { "type": "object", "properties": { "index": { "type": "integer" }, "content": { "type": "string" }, "tokens": { "type": "integer" }, "characters": { "type": "integer" }, "headings": { "type": "array", "items": { "type": "string" }, "description": "Heading breadcrumb of the section the chunk belongs to." }, "pageStart": { "type": "integer", "nullable": true }, "pageEnd": { "type": "integer", "nullable": true } } }, "Stats": { "type": "object", "properties": { "characters": { "type": "integer" }, "words": { "type": "integer" }, "tokens": { "type": "integer" }, "tokenizer": { "type": "string" }, "pagesProcessed": { "type": "integer" }, "ocrPages": { "type": "integer" }, "truncated": { "type": "boolean", "description": "True when a plan limit (pages, rows, OCR pages, archive entries) cut the output short." }, "processingMs": { "type": "integer", "format": "int64" } } }, "ConvertResponse": { "type": "object", "properties": { "success": { "type": "boolean" }, "requestId": { "type": "string" }, "source": { "$ref": "#/components/schemas/SourceInfo" }, "metadata": { "$ref": "#/components/schemas/Metadata" }, "content": { "type": "string", "nullable": true, "description": "The converted document (Markdown or plain text)." }, "contentFormat": { "type": "string", "enum": [ "markdown", "text" ] }, "pages": { "type": "array", "items": { "$ref": "#/components/schemas/Page" }, "nullable": true }, "chunks": { "type": "array", "items": { "$ref": "#/components/schemas/Chunk" }, "nullable": true }, "stats": { "$ref": "#/components/schemas/Stats" }, "warnings": { "type": "array", "items": { "type": "string" } } }, "example": { "success": true, "requestId": "4f1c2a9b8e7d6c5b", "source": { "type": "url", "fileName": "1706.03762", "url": "https://arxiv.org/pdf/1706.03762", "finalUrl": "https://arxiv.org/pdf/1706.03762", "format": "pdf", "mimeType": "application/pdf", "sizeBytes": 2215244 }, "metadata": { "title": "Attention Is All You Need", "pageCount": 15, "creator": "LaTeX with hyperref", "extra": { "format": "pdf", "pdfVersion": "1.5" } }, "content": "# Attention Is All You Need\n\n## Abstract\n\nThe dominant sequence transduction models are based on complex recurrent or convolutional neural networks...\n\n## 1 Introduction\n\n...", "contentFormat": "markdown", "chunks": [ { "index": 0, "content": "# Attention Is All You Need\n\n## Abstract\n\nThe dominant sequence transduction models...", "tokens": 498, "characters": 2210, "headings": [ "Attention Is All You Need", "Abstract" ], "pageStart": 1, "pageEnd": 1 } ], "stats": { "characters": 39581, "words": 6097, "tokens": 9812, "tokenizer": "o200k_base", "pagesProcessed": 15, "ocrPages": 0, "truncated": false, "processingMs": 812 }, "warnings": [] } }, "ErrorResponse": { "type": "object", "properties": { "success": { "type": "boolean", "example": false }, "requestId": { "type": "string" }, "error": { "type": "object", "properties": { "code": { "type": "string", "enum": [ "invalid_request", "invalid_url", "blocked_url", "fetch_failed", "unsupported_format", "empty_input", "file_too_large", "password_required", "invalid_password", "corrupt_file", "ocr_unavailable", "timeout", "rate_limited", "unauthorized", "internal_error" ] }, "message": { "type": "string" } } } } }, "ChunkRequest": { "type": "object", "required": [ "text" ], "properties": { "text": { "type": "string", "description": "Markdown (or plain text) to split." }, "format": { "type": "string", "enum": [ "markdown", "text" ], "default": "markdown" }, "chunkSize": { "type": "integer", "minimum": 64, "maximum": 8192, "default": 512 }, "chunkOverlap": { "type": "integer", "minimum": 0, "default": 64 }, "tokenizer": { "type": "string", "enum": [ "o200k_base", "cl100k_base" ], "default": "o200k_base" } }, "example": { "text": "# Guide\n\n## Install\n\nRun the installer...\n\n## Configure\n\nEdit the settings file...", "chunkSize": 256, "chunkOverlap": 32 } }, "ChunkResponse": { "type": "object", "properties": { "success": { "type": "boolean" }, "requestId": { "type": "string" }, "chunks": { "type": "array", "items": { "$ref": "#/components/schemas/Chunk" } }, "totalTokens": { "type": "integer" }, "tokenizer": { "type": "string" }, "chunkCount": { "type": "integer" } } }, "TokenRequest": { "type": "object", "required": [ "text" ], "properties": { "text": { "type": "string" }, "tokenizer": { "type": "string", "enum": [ "o200k_base", "cl100k_base" ], "default": "o200k_base" } }, "example": { "text": "How many tokens is this sentence?", "tokenizer": "o200k_base" } }, "TokenResponse": { "type": "object", "properties": { "success": { "type": "boolean" }, "requestId": { "type": "string" }, "tokens": { "type": "integer" }, "characters": { "type": "integer" }, "words": { "type": "integer" }, "tokenizer": { "type": "string" } }, "example": { "success": true, "requestId": "4f1c2a9b8e7d6c5b", "tokens": 8, "characters": 33, "words": 6, "tokenizer": "o200k_base" } }, "FormatsResponse": { "type": "object", "properties": { "success": { "type": "boolean" }, "formats": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string" }, "name": { "type": "string" }, "mimeType": { "type": "string" }, "extensions": { "type": "array", "items": { "type": "string" } }, "description": { "type": "string" }, "available": { "type": "boolean" } } } }, "ocrAvailable": { "type": "boolean" }, "pdfOcrAvailable": { "type": "boolean" }, "ocrLanguages": { "type": "array", "items": { "type": "string" } }, "tokenizers": { "type": "array", "items": { "type": "string" } }, "plan": { "type": "object", "description": "Limits of the plan you are calling with.", "properties": { "name": { "type": "string" }, "maxFileMb": { "type": "integer" }, "maxPages": { "type": "integer" }, "maxOcrPages": { "type": "integer" }, "maxRowsPerSheet": { "type": "integer" }, "maxArchiveEntries": { "type": "integer" }, "timeoutSeconds": { "type": "integer" } } } } } } } }