Primitive: /extract · Extract ·
Docling
MultimodalOCR-Document
Overview
Hardware: — drives latency, throughput & cost
| Size | 80M params |
|---|---|
| Tasks | /extract |
| License | — |
| Latency | — |
| Throughput | — |
| Cost | — /1M tok |
Cost is approximate — computed from list GPU prices; your actual price depends on the provider you deploy SIE with.
Extraction
| Output kinds | Parsed Document |
|---|---|
| Inputs | image · document |
| Max sequence length | — |
Benchmarks
olmOCR-Bench
Document text extraction accuracy across arxiv math, old scans, multi-column layouts, and tables
Corpus: 1,403 Queries: 1,403
default
Quality
accuracy 0.3170
ocr
Quality
accuracy 0.3347
Compare (0)Compare →