Choose the plan that's right for your business. All plans include access to our core RAG features.
25M embeddings tokens/month Characters processed for generating vector embeddings
25K retrieval calls/month API calls to search and retrieve from your vector database
10K inference tokens/month Tokens used for AI model responses
5GB vector storage
50 RPM rate limit
7 days log retention
Community support
100M embeddings tokens/month Characters processed for generating vector embeddings
100K retrieval calls/month API calls to search and retrieve from your vector database
50K inference tokens/month Tokens used for AI model responses
25GB vector storage
200 RPM rate limit
30 days log retention
Priority email support
Data connectors included
500M embeddings tokens/month Characters processed for generating vector embeddings
500K retrieval calls/month API calls to search and retrieve from your vector database
250K inference tokens/month Tokens used for AI model responses
100GB vector storage
500 RPM rate limit
90 days log retention
Dedicated support manager
Data connectors included
Custom model fine-tuning
SSO & advanced security
For organizations with specific requirements or high-volume needs.
Custom volume pricing
Dedicated infrastructure
SLA guarantees
Custom integrations
Enterprise SSO
Compliance assistance
On-premise deployment
24/7 support
You'll be automatically charged for additional usage at the rates specified in your plan. We'll notify you when you reach 80% of your plan limits so you can upgrade if needed.
Yes, you can upgrade or downgrade your plan at any time. Upgrades take effect immediately, while downgrades will take effect at the start of your next billing cycle.
Data connectors allow you to easily import data from various sources like Google Drive, Notion, Confluence, SharePoint, and more. They're included in Pro and Enterprise plans.
Yes, we offer a 14-day free trial with no credit card required. You'll get access to all features in the Pro plan with limited usage caps.