Back to explorer

Security at B3IQ

Last updated August 3, 2026

B3IQ builds NVIDIA-powered GPU servers that you own, hosts them in the United States, and operates them as your private AI inference endpoints. This page describes how we protect the data that moves through that service, and how to reach us about a security issue.

Your prompts are not stored

We do not write inference requests or responses to storage. A request is dispatched in memory to the machine that serves it and discarded when the request completes. There is no retention window on prompt content because there is nothing retained.

We do not train on your data and we do not sell it. Machines serving the network are contractually barred from retaining or reusing prompt or completion content.

What we do record, per request, is the metadata needed to route, meter, and pay: a request identifier, timestamp, model, serving machine, token counts, latency, and status. That metadata contains no prompt or completion text, and it is deleted after 90 days.

Your requests go to your machines

B3IQ routes each customer's traffic to that customer's own machines by default. You are not sharing an inference pool with other tenants, and a key can be narrowed further to a named set of machines.

Nothing falls back to a third-party AI provider unless you turn it on. Third-party fallback routing is disabled by default on every account. It is an explicit administrative setting, and it is refused outright for end-to-end encrypted requests.

Encryption

Traffic to B3IQ is protected with TLS in transit. Data at rest lives on our infrastructure provider's encrypted storage. Credentials are never stored in a form we can read back: API keys, access tokens, and recovery codes are stored as one-way hashes and shown to you exactly once, and account passwords are hashed with bcrypt.

End-to-end encrypted inference is available. On this path your client encrypts the request to the serving machine's public key, and B3IQ relays the ciphertext without holding a decryption key: the platform is cryptographically excluded from your content. The machine's encryption key is short-lived and is signed by that machine's own identity key, which your client verifies before encrypting.

To be precise about what that does and does not cover: it protects your content from B3IQ's own systems and from our public surfaces. It does not hide content from whoever operates the machine doing the work. When that machine is yours, that is you.

Access control and accountability

Staff access to production runs through a single-sign-on gateway restricted to our corporate domain, and administrative roles are separated so that read-only, operational, and money-moving actions require different authority.

Every administrative request is recorded in a durable audit log with the actor, the action, the result, and a hashed source address. High-risk actions additionally require a written reason, and the most consequential ones require a typed confirmation before they will execute. Where staff need to diagnose a problem on a machine, they use a time-limited, revocable credential scoped to read-only diagnostics, not a standing login.

Abuse and availability

The service enforces request size limits, token limits, and per-key, per-account, and per-machine rate limits, and supports per-account spend caps and model restrictions. Operators can pause a class of traffic, an account, or a single machine immediately, without a software release, if something needs to be stopped.

Machines that stop responding, fail readiness checks, or report an unhealthy queue are removed from routing automatically.

Live availability is public at status.b3iq.org. It covers the inference gateway, the model catalog API, this website, and the documentation, checked from multiple regions, and it is where we post incidents. It runs outside our own infrastructure on purpose: a status page that goes down with the service it reports on is no use during the outage you needed it for.

How we build and ship

Changes reach production only through reviewed pull requests with automated gates: type checking, unit tests, a dedicated test suite that exercises the billing and settlement path against a real database, static application security testing for both of our languages, dependency vulnerability scanning, and secret scanning. Deployment is automated; nobody ships from a laptop.

Software we distribute is checksummed and its release manifest is cryptographically signed, so the binary you install can be verified against what we published.

Subprocessors

We use a small number of vendors to run the service: our cloud infrastructure and content-delivery provider, payment processors for card and crypto purchases, a transactional email provider, analytics providers, a code-signing service, our source-control and CI provider, and a model artifact repository. A third-party inference provider is used only for accounts that have explicitly enabled fallback routing.

Current customers and prospective customers under assessment can request the itemized subprocessor register, naming each vendor and the data it receives, from the contact below.

What we do not claim

We would rather be useful than impressive, so: B3IQ does not currently hold a SOC 2 attestation or an ISO 27001 certificate, has not commissioned an independent third-party penetration test, does not offer SAML or OIDC single sign-on for customer accounts, and does not use FIPS 140 validated cryptographic modules. We do not offer confidential computing backed by hardware attestation.

If any of these are requirements for your institution, tell us: knowing which ones matter is what determines the order we do them in.

Reporting a vulnerability

Email contact@npclabs.org with the subject line SECURITY, or see /.well-known/security.txt. We aim to acknowledge reports within three business days.

We will not pursue legal action for good-faith research that respects customer data, avoids degrading the service for others, and gives us a reasonable opportunity to fix the issue before disclosure. Please do not access, modify, or retain data that is not yours, and please do not run automated scanning that affects availability.

Security assessments

We maintain a written policy set covering information security, access control, change and patch management, incident response, business continuity, data classification and handling, cryptographic key management, privacy, and AI risk. We complete HECVAT and similar vendor security assessments. Request them from the contact below.

Contact

B3IQ is operated by NPC Labs, Inc. Security and privacy correspondence goes to the address below. See also our Privacy Policy and Terms of Service.

NPC Labs, Inc.1801 N. 16th AvePhoenix, Arizona 85007United Statescontact@npclabs.org

Search B3IQ

Search pages and machines.