Private
Restricts requests to model services with a declared policy of not retaining prompt or response content after inference
Compare LLM API pricing, capability, context and privacy, then use any of them through one OpenAI-compatible API
Restricts requests to model services with a declared policy of not retaining prompt or response content after inference
Hides your Varity account identity from the model service. It does not remove identifying details written inside your prompt.
One catalog
Availability and pricing come from the live Gateway catalog and refresh automatically
You pay what the model service charges per request, with nothing added. A 5% fee applies only when you add credits.