Datalab lite: full-layout OCR at $0.50/1,000 pages, more accurate than Azure Read at half the price
VikParuchuri · x · 2026-10-23
Datalab launched lite mode in its API at $0.50 per 1,000 pages, returning full document structure—text, tables, headings, lists, reading order, and a layout box for every block.
- Benchmarks: 10x cheaper than Azure Layout while scoring higher on text (excluding math) and matching layout; 2x faster on long docs (50-page PDF in 5.0s vs 12.0s for Azure Layout); more accurate than Azure Read at half the price (75.1 vs 42.3 on OmniParseBench docs without math).
- Tech: lite runs Indra OCR, a 1M-parameter model on CPU—that's what makes it cheap.
- Thesis: citing Jevons, Paruchuri argues cheap OCR stops being a budgeted batch job and becomes inline product infrastructure—parse every upload, index whole archives, re-run entire corpora.
- Positioned as "System One OCR"; the larger balanced/accurate modes (91.6/93.5) remain "System Two" for handwriting, math, and degraded scans. 40,000 free lite pages/month.
More from Models
- ChatGPT web can actually listen to audio, but the same model can't via API or Codex — Possible_Statement84 · 2026-10-23
- MiniMax M3.1 Flash free for 3 days on 0G, with 1M context and 512K output — MiniMax_AI · 2026-10-23
- TLA+ expert corrects Grok: TLC only exhausts finite state spaces, not all behaviors — tianyin_xu · 2026-10-23
- Open LLM cost calculator shows Arabic tokenization and 6x price gaps across models — Moham-saed · 2026-10-23
- OpenAI blocks manual reset with 13% usage left: 'no reset needed right now' — AccomplishedSugar490 · 2026-10-23
- Meta's 816B Muse Spark Open scores 39, losing to 180B Qwen3.8-Flash-Next at 40 — BTA_Labs · 2026-10-23