Confidential mode
Run your work through models hosted in a hardware-sealed enclave.
Confidential mode routes your inference through Prem API's confidential compute, an isolated enclave that infrastructure operators and the cloud provider cannot access. It is available on the Confidential plan. You can turn it off later to return future requests to standard provider routing.
What it protects
At the gateway, your request is encrypted for processing and sent to an enclave: hardware-isolated regions of the server that the host OS, the hypervisor, and anyone operating the infrastructure cannot read. The cloud provider can't see your data there. Someone with physical access to the hardware can't either.
Before the gateway, your requests pass through Fluso's infrastructure on AWS. Both the sandbox and gateway run in a secure cloud environment we control.
The enclave itself isn't protected by a policy or a promise. Isolation is enforced in the hardware, and attestation reports signed by the chip vendor let you verify it.
For the full technical picture, see Prem's confidential compute documentation.
Plans
Confidential mode is included with the Confidential plan. Accounts granted access by the Fluso team show Sponsored Confidential as their effective plan.
Open Settings and find Encrypted Inference. Without plan access, the row reads "Available on the Confidential plan" and shows Upgrade. With plan access, it shows an Off or On switch.
Turning it on
Get plan access
Open Settings → Plans and choose Confidential. If your team grants sponsored access, the current plan reads Sponsored Confidential instead.
Enable encrypted inference
Turn on the switch under Settings → Encrypted Inference. The confirmation dialog lists the two unavailable capabilities: automated task generation and image generation. It also explains that you can return to standard inference later, but data removed during activation cannot be restored automatically.
Confirm it's active
The panel turns green and the switch reads On. New inference requests now run through the enclave.
Switching back changes future requests to standard provider routing and makes image generation and automated task creation available again. Existing conversations and context may use standard routing in later requests. Data removed during activation cannot be restored automatically.
FAQ
Can I switch back to normal mode after enabling it?
Yes. Turn the Encrypted Inference switch off and confirm Use standard inference. Future requests use standard provider routing, and image generation and automated task creation become available again.
What happens if confidential inference isn't working?
Confidential mode never falls back to standard inference, because a silent fallback would route your data through a non-confidential path. If the enclave can't be reached, the request fails and you'll see an error instead. Retry once the enclave is reachable again. If it stays down, contact support.
What's disabled while confidential mode is on?
Image generation and automated task creation. Both rely on paths that would take your data outside the enclave, so they're turned off in this mode.
Which plan do I need?
The Confidential plan. Team-granted access appears as Sponsored Confidential.
Can anyone access my data during confidential inference?
Inside the enclave, no. At the gateway, your request is encrypted for a hardware-sealed environment that infrastructure operators and the cloud provider cannot access. Before that, traffic passes through Fluso's AWS infrastructure.