# Nanonets > AI-powered document extraction API. Convert PDFs, images, and documents into Markdown, HTML, JSON, or CSV. ## Docs - [Create Config](https://docstrange.nanonets.com/docs/api-reference-v2/configuration-management/create-config.md): Save a reusable configuration for parse, extract, or classify operations. Returns a `config://` URI that can be referenced in subsequent requests. - [Get Config](https://docstrange.nanonets.com/docs/api-reference-v2/configuration-management/get-config.md): Retrieve a saved configuration by its UUID. - [List Configs](https://docstrange.nanonets.com/docs/api-reference-v2/configuration-management/list-configs.md): List saved configurations with pagination. Optionally filter by config type. - [Batch Classification](https://docstrange.nanonets.com/docs/api-reference-v2/document-classification/batch-classification.md): Classify multiple documents by providing a list of inputs (up to 50). Each document is classified using the same categories and mode. - [Synchronous Classification](https://docstrange.nanonets.com/docs/api-reference-v2/document-classification/synchronous-classification.md): Classify a document into predefined categories synchronously. - [Asynchronous Extraction](https://docstrange.nanonets.com/docs/api-reference-v2/document-extraction/asynchronous-extraction.md): Queue one or more documents for extraction. Accepts a single input or a list of up to 50 inputs for batch processing. - [Synchronous Extraction](https://docstrange.nanonets.com/docs/api-reference-v2/document-extraction/synchronous-extraction.md): Extract structured data from a document synchronously as JSON or CSV. - [Asynchronous Parse](https://docstrange.nanonets.com/docs/api-reference-v2/document-parsing/asynchronous-parse.md): Queue one or more documents for parsing. Accepts a single input string or a list of up to 50 inputs for batch processing. - [Synchronous Parse](https://docstrange.nanonets.com/docs/api-reference-v2/document-parsing/synchronous-parse.md): Parse a document into Markdown or HTML synchronously. Returns the full result immediately. - [Get File Details](https://docstrange.nanonets.com/docs/api-reference-v2/file-upload/get-file-details.md): Retrieve metadata and a signed download URL for a previously uploaded file. - [Upload File](https://docstrange.nanonets.com/docs/api-reference-v2/file-upload/upload-file.md): Upload a document and receive a `file://` URI. Use this URI as the `input` parameter in parse, extract, and classify endpoints. - [Batch Classification (Async)](https://docstrange.nanonets.com/docs/api-reference/document-classification/batch-classification-async.md): Classify multiple documents asynchronously (max 50 files). - [Get Classification Result](https://docstrange.nanonets.com/docs/api-reference/document-classification/get-classification-result.md): Retrieve the status and result of a classification job by its record ID. - [Synchronous Classification](https://docstrange.nanonets.com/docs/api-reference/document-classification/synchronous-classification.md): Classify a single document into predefined categories synchronously. - [Asynchronous Extraction](https://docstrange.nanonets.com/docs/api-reference/document-extraction/asynchronous-extraction.md): Queue a document for background processing. Returns a `record_id` to poll results via `GET /api/v1/extract/results/{record_id}`. - [Batch Extraction](https://docstrange.nanonets.com/docs/api-reference/document-extraction/batch-extraction.md): Process multiple files asynchronously (max 50 files). All files share the same extraction options. - [Streaming Extraction](https://docstrange.nanonets.com/docs/api-reference/document-extraction/streaming-extraction.md): Stream extraction results via Server-Sent Events (SSE) for real-time content delivery. - [Synchronous Extraction](https://docstrange.nanonets.com/docs/api-reference/document-extraction/synchronous-extraction.md): Process a document and return extracted content immediately. (Works for files with 5 pages or less.) - [Chat Completions API](https://docstrange.nanonets.com/docs/api-reference/openai-compatible/chat-completions-api.md): OpenAI-compatible chat completions endpoint. Supports text messages and file/image inputs via `image_url` or `file_url` parts. - [Get Extraction Result](https://docstrange.nanonets.com/docs/api-reference/results/get-extraction-result.md): Retrieve status and result of an extraction job. - [List Extraction Results](https://docstrange.nanonets.com/docs/api-reference/results/list-extraction-results.md): List all extraction jobs for the authenticated user (paginated). - [Architecture](https://docstrange.nanonets.com/docs/architecture.md): Learn about Nanonets Document Extraction API architecture for cloud and on-premise deployments. - [Authentication](https://docstrange.nanonets.com/docs/authentication.md): API keys, Bearer token usage, rate limits, and auth error handling - [Amazon Bedrock Nanonets-OCR Model Import and Inference Guide](https://docstrange.nanonets.com/docs/bedrock-import.md): This guide walks you through importing a nanonets-ocr model into Amazon Bedrock and using it for inference. - [IDP Leaderboard](https://docstrange.nanonets.com/docs/benchmarks.md): NanonetsOCR leads the IDP Leaderboard, outperforming the best document AI models - [Changelog](https://docstrange.nanonets.com/docs/changelog.md): New releases and improvements to the Nanonets Extraction API - [Confidence Scoring](https://docstrange.nanonets.com/docs/confidence-scoring.md): Understand how Nanonets calculates and assigns confidence scores to extracted data. - [Error Handling](https://docstrange.nanonets.com/docs/error-handling.md): HTTP status codes, error response format, rate limits, and troubleshooting - [API Examples](https://docstrange.nanonets.com/docs/examples.md): Complete code examples for the Document Extraction API - [Introduction](https://docstrange.nanonets.com/docs/index.md): Extract content from documents using AI-powered APIs - [MCP Server](https://docstrange.nanonets.com/docs/mcp-server.md): Connect AI assistants to Nanonets document extraction via the Model Context Protocol (MCP). - [Models](https://docstrange.nanonets.com/docs/models.md): Available AI models for document extraction and how to choose the right one - [Output Formats](https://docstrange.nanonets.com/docs/output-formats.md): Supported extraction formats: Markdown, HTML, JSON, and CSV with options and language support - [Quickstart](https://docstrange.nanonets.com/docs/quickstart.md): Go from zero to your first document extraction in under 5 minutes - [Python SDK](https://docstrange.nanonets.com/docs/sdk/python/overview.md): Type-safe Python client for the Nanonets Document Extraction API - [TypeScript SDK](https://docstrange.nanonets.com/docs/sdk/typescript/overview.md): Type-safe TypeScript/Node.js client for the Nanonets Document Extraction API ## OpenAPI Specs - [openapi](https://docstrange.nanonets.com/docs/api-reference/openapi.json) - [openapi-v2](https://docstrange.nanonets.com/docs/api-reference-v2/openapi-v2.json)