Skip to content
  • About
  • Documentation

    Guides & Concepts

    Understand how to use our API on a deeper level. Learn how to use our different endpoints and features.

    Learn more →

    API Reference

    Integrate compliant natural language processing and generation into your products with a few lines of code. 

    Learn more →

    SDK Documentation

    We provide official open-source SDKs (client libraries) for your favorite platforms, These clients make connecting to our API faster and help avoid errors.

    Learn more →

    Compliance, Security & Self Hosting

    We don't store, log, or cache any prompt data flowing through out system. We couldn't train models on your data if we wanted to! Our focus is keeping your data your data.

    Learn more →

  • Events
  • Blog
Get Started
Search icon
Get Started
DEM0

Get Started 

Ready to learn more about Prediction Guard and see if it is a good fit to scale private, secure AI in your organization? Use the form here to give us your contact info. We will reach out to schedule some time with the Prediction Guard team.
 
01 Book a call

Fill out the form here and look for an email to book a time with the Prediction Guard team.

02 Discuss your needs

We’ll take some time to understand your use case, requirements, and deployment needs. We’ll also discuss pricing, timelines, and find the best Prediction Guard solution for you.

03 Place order

Deploy Prediction Guard in your infrastructure with our pre-built and optimized configurations (or get your API key for the managed cloud). Kick start your company's AI transformation with private, secure infrastructure.

Backed by

M25_Logo
IGNITE-FAVICON
sovereigns
Noblis
kstreet
blu
ringbolt
waterstone
bhb
launch
overlook

Frequently Asked Questions

What models do you support?
In our managed cloud (shared) platform, we support the best open LLMs currently available including those from the Llama 3.1, Mistral, and deepseek families. In single-tenant deployments, you can tailor the model mix to fit the needs of your company!
How does Prediction Guard protect our data?
We don't store, log, or cache any prompt data flowing through our system. If you are self-hosting Prediction Guard, you can even keep the deployment air-gapped. We couldn't train models on your data if we wanted to! We also enable you to filter PII, anonymize data injected into prompts, filter prompt injections, and more in accordance with NIST and OWASP recommendations. For customers leveraging self-hosting, data doesn't even leave your network(s).
Can I use LangChain and LlamaIndex?
Yes! We love LangChain and LlamaIndex! In fact, we have officially supported PG integrations in the LangChain codebase.
How can I integrate my company data?

95% of use cases can be solved using a methodology called "retrieval augmentation". This is great, because all data can stay within your company's infra and be injected into the privately hosted models without that data flowing back to the creators of those models.

Are you HIPAA compliant?

Yes. We can sign a BAA.

"Prediction Guard is directly impacting our ability to provide timely decision support
in the most challenging environments."

John Chapman | Product Strategy Lead, SimWerx