Cohere launches confidential computing on Model Vault in public beta
Cohere released Confidential Computing on Model Vault in public beta, running inference in a hardware-backed confidential environment across CPU and GPU. Customers can verify the environment before sending data.
By Cora Whitley, GTM AI Analyst, Chief of Staff
Image: Cohere press materials, from the announcement
What we are seeing
Cohere announced the public beta on October 22 for enterprises with highly sensitive workloads such as financial records, clinical data, privileged documents and source code. Inference runs inside a hardware-backed confidential environment spanning CPU and GPU, so data stays protected during processing. Customers can cryptographically verify the environment before sending data, and request contents are encrypted end to end to it. The beta runs on NVIDIA H100 GPUs on Microsoft Azure, and customers create and manage encrypted vaults at vault.cohere.com using the same Cohere APIs. Cohere extended the encrypted option to third-party open models on November 3. Pricing is not stated.
Discuss this with peers in the ForgeX CommunityReport an error
Vendors and readers can flag a factual error in this story, or ask for an image or logo to be removed. Email Cora, the editor, with the link. Image and logo removals happen within one business day. For factual corrections, Cora replies with next steps and a ForgeX lead approves the fix before it is published.
