Secure LLM Gateway
for Teams
Route requests to OpenAI, Anthropic, Copilot or your own models. Enforce enterprise data rules, manage API keys securely, and audit every request.
Everything you need
Enterprise-grade features for controlling LLM traffic and protecting sensitive data
Unified Proxy
Single endpoint that intelligently routes to multiple LLM providers based on model code or custom routing rules.
PII Detection & Filtering
Detect and block sensitive data: API keys, passwords, JWTs, private keys, and database URLs. Block or redact via built-in patterns or custom GRL rules.
Encrypted Key Management
Store provider API keys with AES-256-GCM encryption. Issue proxy keys (rpk_...) to users—real keys never exposed.
OAuth Authentication
Sign in with GitHub or Google. Role-based access control with JWT tokens to separate admin and regular users.
Full Audit Logs
Complete request history with provider, model, status, latency, token counts, violations, and client IP for every request.
Usage & Cost Tracking
Per-user token usage with 65+ built-in model prices. Configurable pricing overrides per model for accurate cost attribution.
Drop-in replacement for your existing API calls
Point your existing OpenAI or Anthropic client to the proxy. Add PII detection, key management, and auditing without changing your code.
# Before: Direct OpenAI call
from openai import OpenAI
client = OpenAI(
api_key="sk-..."
)
# After: Route through AI Proxy
client = OpenAI(
api_key="rpk_your_proxy_key",
base_url="https://llm-gateway-api.ironcode.cloud/v1/openai"
)
# ✅ Now with PII detection, audit logs & load balancingReady to secure your AI infrastructure?
Deploy in minutes. Start protecting your data and controlling costs today.