Premium private inference
Pricing and limits
Three monthly private inference plans for ultra-fast, privacy-first access.
Monthly private inference plans
All plans include privacy-first processing and clear capacity tiers.
Premium
Complete focused tasks with Flash.
For focused builders completing tasks with Flash and predictable monthly access.
Features
2 max concurrent requests
Privacy-first processing
Prompts and responses are not used for training
Growth
Most popularComplete more work with Flash.
For teams completing more work with Flash without trading away speed or data control.
Features
5x usage
8 max concurrent requests
Privacy-first processing
Prompts and responses are not used for training
Scale
Highest capacityPut Flash behind demanding workflows.
For demanding workflows that need our highest monthly Flash capacity with privacy-first processing.
Features
15x usage
Privacy-first processing
Prompts and responses are not used for training
Flash plans are limited to the approved cohort while Teralor is at capacity. Join the waitlist for access.