From the team
OpenParser blog
Engineering notes from the OpenParser team: extraction, lineage, and review.
How to compare OCR models on your own documents
Run the same PDFs through PaddleOCR-VL, GLM-OCR, and cloud OCR APIs with one script, then compare text, tables, and cost per page before you switch models.
2 min readEngineeringOctober 28, 2026Hosting GLM-OCR on one L4 GPU: what we measured
How OpenParser serves Z.ai GLM-OCR with vLLM behind the PaddleOCR layout-parsing contract, with throughput, memory, and cost per page on an NVIDIA L4.
2 min readProductOctober 28, 2026An OpenRouter for OCR: offering many OCR models in your product
Why platforms that parse documents should let users pick an OCR model, and how to add PaddleOCR-VL, GLM-OCR, Mistral, Azure, Google, and Textract behind one API.
2 min readGuidesOctober 28, 2026Call the PaddleOCR API from Java and Spring Boot
Parse PDFs with hosted PaddleOCR-VL or GLM-OCR from a Spring Boot app: multipart upload with RestClient, typed JSON records, and async jobs for large files.
2 min readEngineeringAugust 27, 2026Making document extraction confidence traceable
Track confidence through parsing, extraction, and transformation so uncertain fields can be sent for targeted human review.
4 min read