Pricing

All prices include hardware-enforced integrity, privacy and verifiability by TEEs.

On-demand usage. Pay for what you use.

Up to 80% cheaper than confidential computing on hyperscaler clouds.

For enterprise licensing and on-prem deployments, see Enterprise.

Confidential Inference

ModelInput (per 1M tokens)Output (per 1M tokens)
GLM 5.1$1.00$3.50
Qwen 3.5 35B$0.25$2.00
DeepSeek V3.2$0.40$0.60

Additional models available on request: founders@confidential.ai.

Confidential VMs

GPU VMs — billed per GPU-hour.

GPUVRAMHost CPU TEEPer GPU-Hour
RTX PRO 600096 GB GDDR7AMD SEV-SNP$1.50
H10080 GB HBM3AMD SEV-SNP or Intel TDX$2.00
B200192 GB HBM3eIntel TDX$5.00

CPU VMs — billed per vCPU core-hour, plus per GB-hour of RAM.

TEE BackendPer Core-HourPer GB-Hour (RAM)
AMD SEV-SNP$0.05$0.012
Intel TDX$0.05$0.012

Attestable Builds

Base rate: $0.008 per vCPU-minute. Runners scale linearly.

RunnerSpecsPer Minute
Standard2 vCPU, 8 GB$0.016
Medium4 vCPU, 16 GB$0.032
Large8 vCPU, 32 GB$0.064
XL16 vCPU, 64 GB$0.128

Getting Started

Let us know what you need: founders@confidential.ai.