PDF template engine and rendering API that generates pixel-perfect documents in milliseconds
A typed decision API for routing, classification, and scoring
Stage
Not given
Not given
Founded
Not given
Not given
Based in
AE
CA
Pricing model
Freemium
Paid
Pricing
Starter: $19/month (1,000 PDF renders, 1,500 AI design credits). Pro: $49/month with 7-day free trial (5,000 PDF renders, 4,000 AI design credits). Scale: $99/month (20,000 PDF renders, 10,000 AI design credits). Platform: $199/month (50,000 PDF renders, 15,000 AI design credits, embedded editor). A
$0.040 USD per million input tokens; output is free
Key features
170+ starter templates for invoices, receipts, certificates, and reports
AI-assisted template design with plain English chat interface
Live preview with instant rendering as templates are edited
REST API for programmatic PDF generation with millisecond response times
Version control to track, rollback, and compare template edits
Model Context Protocol (MCP) support for AI agent integration
Webhook notifications for asynchronous render completion
Batch generation for rendering thousands of documents in parallel
Team workspaces with role-based access and shared brand assets
Embedded editor SDK for white-label integration in SaaS products
Choice question type with multiple options and probability scores
Boolean question type for true/false judgments with probability
Score question type with min/max range and level probabilities
Filter list endpoint for ranking JSON items by instruction match
Support for image and audio input with Crossroads-M model
Idempotency keys for safe retries without duplicate charges
Rate limiting with 120 requests per minute default and 4 concurrent requests
Multiple question types per request with single round trip
What makes it different
Uses Typst open-source typesetting engine instead of headless browsers for predictable page breaks and table behavior
Median render time of approximately 220 milliseconds without complex setup or headless browsers
AI assistant that describes changes in plain English while maintaining inspectable template source code
Supports JSON schema binding with live preview for dynamic variable testing before deployment
Native AI agent integration via Model Context Protocol for document generation without custom code
Returns probability scores for every answer to guide decision-making confidence
Supports image and audio analysis alongside text with dedicated audio-trained model
Filter lists by instruction match without writing text generation code
Typed output constrains format while preserving flexible judgment logic
pdfs.build
Crossroads