Not just extraction. Onboard users, deploy pipelines, process documents, manage synonyms, export results — all through REST endpoints. Zero UI required.
Send any document. Get structured, catalog-matched data back. That's it.
1 Submit a document
2 Poll for results
3 Use the structured data
Most platforms give you an extraction endpoint. Monce gives you the entire lifecycle — onboarding, deployment, processing, and management — all programmable.
Upload articles catalog, client list, sample documents, and schema. 4 endpoints, fully automated.
POST /upload/articles
POST /upload/clients
POST /upload/samples
POST /upload/schema
Trigger pipeline training — matchers, prompts, validation. Poll for progress.
POST /deploy/{user_id}
GET /deploy/{user_id}
Send any document. Get structured, matched, priced data. Batch supported.
POST /extract
GET /extract/{task_id}
Synonyms, history, exports (CSV/XLSX/PDF), dashboard stats — all via API.
GET /extract/{id}/export
GET /synonyms/api/fields
GET /extract/history
The assistant (concierge + extraction) is also an API endpoint. Send text, files, or both. Deployed users get extraction + editing. Non-deployed users get guided onboarding.
GET /extract/{task_id} returns this when status: "completed":
Base URL: https://monolith.aws.monce.ai — All endpoints return JSON unless noted.
Monce exposes an MCP (Model Context Protocol) server. Your AI agent can call Monce tools directly — extract documents, check status, query catalogs — without writing HTTP code.
MCP support is in active development. Contact us for early access.
20 cents per line. First 100 lines free. No API key required for sandbox.
100K+ lines/month? Contact us for volume pricing.