AI firewall + verifiable audit trail

Prove what your AI does
with your customers' data.

Senthex is the AI firewall between your app and OpenAI, Anthropic, Mistral or Gemini — and the verifiable audit trail that proves what your AI saw and produced. 26 shields. EU-hosted.

Built for teams shipping LLMs to production

Proof, not promise

Verify it yourself

Most AI-security tools ask you to trust them. Senthex gives you a verifiable record. Below is a real (synthetic) audit bundle — change one byte and watch the cryptographic chain catch it, live in your browser.

Flip the blocked attack's score 0.86 → 0.06 — an insider trying to hide it.

A normal log

Editable. Nothing proves it wasn't changed.

{ "event": 13, "verdict": "block",
  "injection_score": 0.86 }

No integrity check — the edit is invisible. “Trust us.”

Senthex verifiable registry

A SHA-256 hash chain, anchored to an independent timestamp.

"chain_ok": true·exit 0
Integrity verified

External anchor: freeTSA — an independent RFC 3161 timestamp (public demo authority, not eIDAS-qualified), checked by the offline verifier.

18 LLM calls · project acme-talent-prod
#VerdictInjectionrow hash
Maps to EU AI Act Article 12 (automatic record-keeping) & Article 19 (≥ 6-month log retention) — not Article 15.

100% synthetic data (ACME Talent GmbH). This proves integrity — the records form an unbroken chain that wasn't silently rewritten before the timestamped anchor. It does not prove completeness (a snapshot can omit events) or origin (a signature comes later). Tamper-evident, not tamper-proof. The verifiable audit trail is a pilot capability (v1.1.7), not yet the published release.

Loading the proof bundle…
Integration

One line. That's it.

Change your base_url. Everything else stays the same — your API key, your SDK, your existing code.

your_app.py
Before
from openai import OpenAI
 
client = OpenAI(
api_key="sk-..."
)
After

Every request is now intercepted, scanned across 26 shields, and logged. Your existing code requires zero changes.

By design

Built for production.

Streaming pass-through. EU-hosted. Data minimisation by default.

0

line to integrate

swap your base_url — keep your SDK and key

0

shields per call

input and output — best-effort, not exhaustive

0

LLM keys stored

your provider key is forwarded in-flight, never persisted

0

LLM providers

OpenAI · Anthropic · Mistral · Gemini · OpenRouter

How it works

Defense in depth, without the complexity.

Universal compatibility

One line. Every provider.

No SDK to install. No refactor required. Swap your base_url to app.senthex.com/v1 and every request — across every provider — goes through Senthex's shield layer. Transparent by design.

Your App
Senthex Shield
OpenAI
Anthropic
Mistral
Gemini
OpenRouter

Threat detection

Defense in depth.

26 shields run on every request — prompt-injection patterns, PII detection (redacted before the model when you run redact mode), secret-leak and unicode-steganography checks. Pattern-based and best-effort: no filter is exhaustive (OWASP ranks prompt injection LLM01). That's exactly why the real assurance is the verifiable audit trail, not the shield alone.

Injection
PII
Secrets
Unicode
Behavioral
Semantic
Response
Budget
Canary
Integrity
Hardening
Multi-Turn
Classifier
Toxicity
PII Backref
Code Danger
Compliance
Consistency
Validator
Tagger
Intent
Bypass
Tool Calls
Rate Limiter
Sanitizer
Credit Card

Observability

See everything. In real time.

Every request is logged, scored, and classified. Threat timeline, anomaly detection, per-project analytics. Export your full audit trail for EU AI Act compliance in one click.

Live feed
PASSNone43ms
WARNPII (redact mode)46ms
PASSNone41ms
BLOCKPrompt injection45ms
PASSNone44ms

Compliance

Built for the EU AI Act.

Senthex supports record-keeping under Articles 12 & 19: an audit trail, data classification and exportable reports. Data minimisation by default. Hosted in Germany. High-risk obligations were provisionally postponed to December 2027 — but regulated buyers ask you to prove what your AI does well before the law compels it.

EU AI Act
Ready

Deadline: August 2, 2026

Why Senthex

The independent alternative.

Senthex
CloudflareLakeraLLM Guard
One-line integration
Behavioral fingerprinting
Unicode steganography
EU AI Act audit trail
Canary tokens
Multi-turn tracking
Self-hosted option
Startup-friendly price

Lakera, Protect AI, Prompt Security — all acquired in 2025. Senthex is the independent, European-built option for startups and scale-ups.

Pricing

Simple, transparent pricing.

Start on the free tier. No credit card required. Upgrade when you need to.

Free

€0/mo

1,000 requests / month

Start free
  • [QUOTA À CONFIRMER] requests/month
  • All 26 shields
  • Real-time dashboard
  • 3-day log retention
  • Community support
Popular

Pro

€20/mo

50,000 requests / month

Upgrade to Pro
  • [QUOTA À CONFIRMER] requests/month
  • All 26 shields
  • Real-time dashboard
  • 14-day log retention
  • Webhook alerts
  • CSV export
  • Email support

Business

€99/mo

500,000 requests / month

Upgrade to Business
  • [QUOTA À CONFIRMER] requests/month
  • All 26 shields
  • Real-time dashboard
  • 90-day log retention
  • EU AI Act audit trail
  • Webhook + Slack alerts
  • Priority support
  • OWASP LLM Top 10 report

Self-host

Contact us

Deploy in your own environment

Contact us
  • Deploy in your own environment — no data leaves
  • All 26 shields
  • Updates included (security + AI Act)
  • Offline audit-trail verifier
  • Art. 12 & 19 record-keeping
  • Onboarding & deployment support
  • Best-effort email support (48–72h)
Security

Ready to secure
your LLM stack?

Start on the free tier. No credit card required.

No credit card required · EU-hosted · GDPR compliant