Cohere opens public beta of Model Vault confidential inference on H100s via Azure
Cohere
On October 22, 2026 Cohere opened a public beta of Confidential Computing on Cohere Model Vault, running its serving stack inside a confidential VM with GPU memory protected from host and infrastructure operators. Request payloads are encrypted to the attested environment using Oblivious HTTP, and clients verify signed evidence of hardware, firmware and software before sending data. The beta runs on NVIDIA H100 GPUs on Microsoft Azure, with Blackwell B200 support planned.
Why it matters
Hardware attestation strong enough that a customer refuses to send data on failure is what regulated enterprises need before putting sensitive workloads on a third-party inference API.
Importance: 2/5
new feature beta