Folder file system
Keep your documents in a familiar folder structure.
- Research
- Acme
- Annual report.pdf
- Q4 earnings.pdf
- Investor letter.pdf
- Market reports
The PageIndex Agent
Vectorless RAG for long, complex documents — accurate, traceable, context-aware, and cost efficient.
Understands document structure. Uses fewer tokens.
PageIndex Agent will generate and understand your document’s tree structure, so it reads the relevant sections and keeps token costs low.
Coming to PageIndex Agent soon
Finds the right pages. Gets answers faster.
With Page Search, PageIndex Agent quickly locates relevant pages and gets to the answer sooner.
Document Management
Organize documents in folders, or bring them together in collections with metadata.
Visual understanding, with visual citations
Understand charts, tables, and page layouts. See the evidence directly on the PDF, with the relevant region outlined.
Read beyond the text
The evidence, in view.
Connect an answer to the diagram or table it comes from. Visual citations point to the specific region on the original page.
Select a citation to highlight its source.
Compatible and Scale with any LLMs
Bring your preferred LLM. PageIndex handles retrieval, so you can choose the balance of accuracy and cost that works for you — and switch models as your needs grow.
Illustrative · frontier among selected modelsExplore the benchmark
Compare with Vector RAG
PageIndex gives LLMs a persistent structure to retrieve only the information they need.
vs Vector RAG
More accurate, at lower cost
Answer accuracy
Cost per 1,000 queries
63 questions on NVIDIA's 10-Ks, six embedding models at top-k 10 to 100. Every system answers with the same model and is graded against reference answers.
Run it anywhere
The same SDK runs on your laptop, on our cloud, or inside your own private cloud.
PageIndex Local
Open source, on your machine, with your own model key.
- Documents never leave your disk
- Cost-efficient indexing with PageIndex Flash
- Text-based PDFs, read directly — no OCR
- Open source, 35k+ stars on GitHub
PageIndex Cloud
Managed indexing, storage, and retrieval. Nothing to run.
- Our best indexing model, fully managed
- Scanned files and image understanding
- Hosted storage and file management
- Free to start — 30k+ developers already building
PageIndex Enterprise
All of Cloud, deployed in your own private cloud.
- Runs in your VPC on AWS, Azure, or GCP
- Documents and indexes stay in your cloud
- customized integrated options
- Audit logs, dedicated support, and SLA
Simple usage billing for PageIndex Cloud#
Local stays free and open source. Start with $10 in free Cloud credits. No minimum monthly cost.
Free Starter
$10in free credits
- No payment method required
- Index up to 10,000 pages$10 in credits indexes 1,000 pages, or up to 10,000 with Flash. Flash is $0.001 per page, rounded up to the next 10 pages per document, for text-based PDFs and Office files.Pricing details →
- 1,000 active pages free, every month
- Unlimited retrieval on your active pages
- Bring your own LLM
Usage Billing Rates
I havepagesFlash builds the tree from the PDF's own layout, so it's fast and low-cost. For text-based PDFs; citations point to pages, not lines.Without Flash, every page is read with OCR and a model, so scanned and image-heavy documents work too, with line-level citations.Pricing details →
Indexingone-timeScanned and image-heavy documents work too. Line-level citations.$0.01 / page$10.00
Active pagesKept indexed and ready to query. First 1,000 free.$0.001 / page / mo$0.00/ mo
RetrievalNo retrieval fees on active pages. You pay your LLM provider directly.Unlimited