agentbody/document-parse
Parse a document at an HTTPS URL into Markdown and structured content. Supports PDFs, Word documents, and other common formats. Returns page count, metadata, and full Markdown extraction.
Input
Idle
Example output — click Run to generate your own
API README
Document Parse
Parse documents from HTTPS URLs into clean Markdown with structured content extraction.
Highlights
- Converts PDFs, Word docs, and other formats to Markdown
- Preserves headings, tables, lists, and formatting structure
- Optional chart analysis and table merging
- Returns document ID for page-level retrieval via GET endpoint
Pricing
| Component | Price |
|---|---|
| Per document parsed | $0.01 |
| Document retrieval (GET) | Free |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| Converting PDFs to Markdown for RAG | Local file uploads (URL input only) |
| Extracting structured data from reports | Image-only documents without OCR |
| Research paper analysis | Base64 or multipart uploads |
| Contract/legal document processing | Real-time document monitoring |
Technical Specs
| Spec | Value |
|---|---|
| Method | POST |
| Endpoint | /v1/documents/parse |
| Input | HTTPS document URL + filename |
| Output | Document ID, page count, Markdown, metadata |
| Retrieval | GET /v1/documents/{document_id} (free) |
| Execution | Sync |
| Idempotency | Requires Idempotency-Key header |