Start for free. Scale when your agents ship.
One retrieval API and hosted MCP server over your own sources. Every plan returns accurate, cited context.
14 days to build against your own sources.
One index with limited usage
Retrieval API and hosted MCP
Accurate, cited context
Pre-built agents and integrations
For agents running in production.
Production API and hosted MCP
Continuous sync across standard, private, and authenticated sources
Analytics, pre-built agents, and integrations
Email and Slack support
For governed and global deployments.
SSO, SCIM, and advanced access controls
Audit logs and data retention controls
EU and regional hosting
Premium support
Included
Every plan includes
Ingest
Building data connectors
Crawling complex websites (with JS)
Converting PDFs and images
Index
Handling incremental data indexing
Designing optimal conversion and chunking
Choosing embeddings/storage strategy
Retrieve
Building retrieval harness (grep, semantic)
Optimizing recall/accuracy
Tuning context size and num results
Operate
Owning vector/filesystem infra
Migrating when new models come out
Providing analytics for the business
The most accurate retrieval API over your product knowledge.
Give your agents the context they need to do reliable work in production.