Document to markdown
Uses: /extract
Send a document to /extract and get structured text back — OCR, layout, tables and reading order resolved into markdown your agents can read.
Featured models
Extract · /extract
| Model | Size | Quality | Latency | Throughput | Cost $/1M | |
|---|---|---|---|---|---|---|
| zai-org/GLM-OCR MultimodalMultilingual | 1.3B | — | — | — | — | |
| PaddlePaddle/PaddleOCR-VL-1.5 MultimodalMultilingual | 959M | — | — | — | — | |
| docling MultimodalOCR-Document | 80M | — | — | — | — | |
| No models match. | ||||||
Measured on L4; other hardware shows "—" until benchmarked. Pick a benchmark to rank by quality.
For similar models, browse the full
/extract catalog →
Examples
End-to-end projects from our examples that put this task to work.
Swap an OCR model with one identifier change
A recognition VLM, an end-to-end document model and zero-shot NER, all driven by the same extract call.
Multimodal wine recommender with OCR Preference-based wine retrieval and reranking paired with OCR label detection in one flow.
Featured picks are still being finalized. Latency, throughput and cost are real where we've benchmarked the model on the selected GPU; "—" means no measurement there. Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Compare (0)Compare →