Pulse
Pulse uses OCR, layout detection, and vision models to extract text, tables, charts, and structured data from documents.
What it does
- Document extraction
Features 4
- Layout-aware document understandingUnderstands page structure before reading content, identifying tables, charts and text.
- Reading order for irregular layoutsProcesses multi-column and irregular layouts in a human-like sequence.
- Private VPC and on-prem deploymentRuns entirely inside a customer VPC or on-prem environment on major hyperscaler networks.
- Chart, table and figure conversionUses fine-tuned vision-language models for chart, table and figure conversion.
Sources
- Pricing
-
Pricing page: "Free up to 20k credits"
- Description
-
Official documentation · 5 Nov 2026
Product page: "Pulse uses OCR, layout, and vision models"
- What it does
-
Official documentation · 5 Nov 2026
Product page: "Pulse uses OCR, layout, and vision models"
- Sold within
-
Sold on its own with published plans.
- Name
-
Official documentation · 5 Nov 2026
Name as published on the product page.
- URL
-
Official documentation · 5 Nov 2026
Product page, read 2026-11-05.
- Deployment
-
Official documentation · 5 Nov 2026
Product page: "On‑prem, VPC or air‑gapped deployments"
- Interfaces
-
Official documentation · 5 Nov 2026
Product page: "On‑prem, VPC or air‑gapped deployments"
Something wrong here? Send a correction — quote this product id: pulse-platform.