Why Confidential AI?
Traditional cloud AI deployments expose your models and data to the cloud provider. Confidential AI addresses this by running everything inside hardware-protected TEE. Your models stay private, your data stays secure, and you get cryptographic proof that execution happened in a trusted environment. Confidential AI has these essential features of inferencing pre-deployed LLMs, deploying custom models, or using entire GPU infrastructures with TEE to protect your models and data.Confidential AI API
Try LLM inference API nowPre-deployed LLM inference API with OpenAI-compatible interface
Confidential AI Models
Try inference your own AI modelsDeploy and manage AI models in a secure, confidential computing environment
Confidential GPU
Try to deploy your own models on GPU TEERent dedicated GPU TEE servers for custom model deployment
Quick Tour of Confidential AI
API and Models
Use API introduces pre-deployed LLMs with OpenAI-compatible APIs for quick integration. For advanced use cases, Tool Calling enables LLMs to interact with external tools and APIs securely within TEE.Confidential GPU
Model Template lets you deploy and manage custom AI models in GPU TEE if current models in API do not meet your needs. For complete infrastructure control, you can use Confidential GPU to deploy custom models for inference or training/fine-tuning. Configure GPU, CPU, RAM, and storage to match your exact workload needs.Verify Attestation and Signature
To ensure your workloads run securely in TEE, you can Verify Attestation to check the TEE hardware, operating system, source code, and distributed root-of-trust attestations. Then you can Verify Signature to confirm the integrity of your Confidential AI API requests and responses.Benchmark
Our performance benchmark shows TEE mode on H100/H200 GPUs runs up to 99% efficiency, nearly matching native performance. This means you get confidential computing with minimal performance penalty.FAQs
Check FAQs for frequently asked questions about Confidential AI.What makes Phala Cloud Confidential AI Different?
- Seamless integration: Drop-in OpenAI API compatibility with popular models (DeepSeek, Llama, GPT-OSS, Qwen) ready for immediate use
- Verifiable security: Hardware-enforced privacy with cryptographic attestation proving execution in genuine TEE environments
- Flexible deployment: Choose from pre-deployed APIs, custom model hosting, or dedicated GPU infrastructure with full configuration control