Document Parsing
Extract structured markdown from PDFs or ordered image batches.
Standard$0.005/ page
Max$0.008/ page
Standard Ultra 2$0.008/ page
Experimental$0.005/ page
Legacy$0.005/ page
Cost-Efficient$0.002/ page
Pay As You Go
Simple pricing for the document context pipeline.
No subscriptions and no minimum commitments. Use one credit balance across parsing, indexing, search, and grounded AI responses.
Document Indexing
Build retrieval indexes over parsed document context.
Vector$0.10/ 1M tokens
Hybrid$0.50/ 1M tokens
Search
Query indexed documents with vector or hybrid retrieval.
Vector$0.01/ query
Hybrid$0.05/ query
AI Responses
Generate grounded answers over retrieved document context.
Fast input$1.00/ 1M tokens
Fast output$5.00/ 1M tokens
Pro input$3.00/ 1M tokens
Pro output$16.00/ 1M tokens
How usage becomes cost
1
Upload and parse
Send a PDF or ordered image batch. The parser emits structured markdown and page metadata.
2
Index context
Build vector or hybrid indexes depending on latency, exactness, and document complexity.
3
Search and answer
Run search or grounded responses. Charges are metered by query and token usage.
Enterprise and high volume
Processing large document volumes or need dedicated infrastructure? We can support custom contracts, priority support, volume pricing, and deployment requirements.
Frequently asked questions
Do I need a subscription?
No. Infratex is pay-as-you-go. Add credit to your account and use it across parsing, indexing, search, and responses.
How are pages counted?
Parsing is metered by document page or ordered image page. Each parser method has a flat per-page rate.
What is the difference between Vector and Hybrid?
Vector is fast and cost-effective. Hybrid adds structural document understanding for tables, identifiers, and audit-heavy workflows.
How are response tokens counted?
Input tokens include retrieved context and the prompt. Output tokens are the generated answer. Both are metered separately.