šŸš€ Confidential AI coding assistants are here! Get started now.

The AIĀ API with zero data exposure

With Privatemode, you get on-prem like privacy combined with the convenience and flexibility of the cloud.

API_diagram

Your data never leaves your control.

Privatemode is the first AI API service to offer true end-to-end privacy using hardware-based confidential computing. Simply run the Privatemode Encryption Proxy, which provides an OpenAI-compatible API while seamlessly encrypting your data.

Your data remains encrypted at all times – only the AI can process it within its secure, confidential computing environment.

As easy as 1-2-3.
As secure as it gets.

Run the Privatemode Encryption Proxy.

docker run -p 8080:8080 \
  ghcr.io/edgelesssys/privatemode/privatemode-proxy:latest \
  --apiKey <your-api-token>

The proxy verifies the integrity of the Privatemode service using confindential computing-based remote attestation. The proxy also encrypts all data before sending and decrypts data it receives.

Send your prompts to the proxy.

curl localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ibnzterrell/Meta-Llama-3.3-70B-Instruct-AWQ-INT4",
    "messages": [
      {
        "role": "system",
        "content": "Hello Privatemode!"
      }
    ]
  }'

The proxy is compatible with the OpenAIĀ Chat API.

Done!

You now have programmatic access to an end-to-end secure AI. Process your own sensitive data or provide trustworthy services to others – the possibilities are endless.

Features you'll love.

End-to-end confidential computing

Privatemode enforces hardware-based runtime encryption and remote attestation at every stage, leveraging AMD SEV-SNP and Nvidia H100 confidential-computing features.

Lock filled

State-of-the-art AI models

Access Llama 3.3 70B (quantized) or other high-performance models like DeepSeek R1 (coming soon).

High performance

Process > 1,000 tokens per second with consistent low-latency responses.

Drop-in OpenAI compatibility

Seamlessly switch from OpenAI to our compatible chat API.

Cost transparency

Monitor token usage in real-time and pay only for what you use.

The scalability of the cloud.
The security of on-prem.

Features

Data privacy

Compliance

Setup time

Infrastructure costs

Maintenance

Scalability

Privatemode

included icon

Enforced by confidential computing

included icon

By design

included icon

Minutes

included icon

None

included icon

Fully managed

included icon

Automatic

ChatGPT

excluded icon

Contractual

excluded icon

Limited

included icon

Minutes

included icon

None

included icon

Fully managed

included icon

Automatic

Self-hosted AI

included icon

Full control

included icon

Full control

excluded icon

Weeks to months

excluded icon

High upfront

excluded icon

Self-managed

excluded icon

Manual

Why use Privatemode?

Get on-prem level privacy without the overhead

With Privatemode, you get a dynamically scalable API that offers the same confidentiality as an on-premise solution – minus the infrastructure costs and complexity.

Streamline compliance discussions

Privatemode provides a turn-key technical solution to your internal and external discussions on data privacy, data security, and compliance in connection with AI.

Focus on innovation, not infrastructure

With Privatemode, you can focus on building your product and instead of building out your own AIĀ model hosting capabilities.

Automate with confidence

With Privatemode, you can even process your sensitive data with AI.

Logo

Made in Germany