🛡️ PII Shield NEW
Your passwords and personal data never reach the LLM.
Run DeepSeek Harness, Claude Desktop, ChatGPT or Codex on 19 AI models (DeepSeek, Qwen, GLM, Kimi, Grok + Claude/Gemini) with one API key. The PII Shield de-identifies sensitive data before routing — and restores or redacts it on the way back, exactly as you choose.
client = OpenAI(base_url="https://api.aiorouter.ca/v1", api_key="...")
You choose: Restore or Redact
AIOrouter replaces your sensitive values with placeholders before the LLM sees them — then restores them on the way back (Restore) or never restores them (Redact). You decide, per API key, per data type.
- Restore : the AI sees only a placeholder — you get the real answer back.
- Redact : secrets (passwords, API keys) are removed on the way in and never restored — the AI cannot write them back anywhere.
- Per-type control: e.g. restore your name, but redact SIN / passwords.
- ⚠️ Shield Disabled : the PII Shield is off — your real data (name, email, passwords) goes straight to the LLM. Only for a trusted provider with no sensitive data; strongly discouraged.
🧪 Try it: switch the profile and see what the AI sees
⚠️ Shield Disabled — your real name, email, passwords and API keys would go straight to the LLM. Only consider this on a trusted provider with no sensitive data.
S-A · “Passwords can never be written back”
For: Everyone
Connected directly: the password could be written into chat, notes, or commits.
The LLM sees only a placeholder and never restores → the real password can never be written back.
Setup: “standard” profile (technical secrets = redact)
S-C · “SIN — zero leakage”
For: Employees, HR, finance
The SIN could be displayed in the reply or written elsewhere.
The UI and every output show only a placeholder — the real SIN never appears.
Setup: CANADA_SOCIAL_INSURANCE_NUMBER → redact (or “safe” profile)
S-D · “Protect the developer’s .env”
For: Developers
The AI could paste a key into generated code.
No real secret in generated code or in chat.
Setup: “standard” profile (technical secrets redacted by default)
Claude & Codex MCP — advanced overview
The key idea: the model does not receive your original sensitive values
AIOrouter is designed as a control layer between your product and AI providers. Personal information and technical secrets are protected before routing, while useful context remains available for the AI task.
Your OpenAI SDK sends a normal request to AIOrouter.
AIOrouter detects sensitive data and keeps control logic in the Canada-resident layer.
The provider receives replaced context, not the original sensitive values.
The response returns through AIOrouter before it reaches your application.
Why this matters: You can keep useful AI workflows while avoiding exposure of original personal data or technical secrets to the provider model.
Why AIOrouter is different
Not just a model router
Generic routers simplify model access. AIOrouter adds a protection and control layer designed for Canadian teams.
One integration — 20+ models
Use Claude, Gemini, DeepSeek, Qwen, GLM and Kimi through an OpenAI-compatible API. Change models without rebuilding your product.
Useful privacy, not destroyed context
Protection happens before provider routing so support, document and code workflows remain practical without exposing original sensitive values.
Predictable spend
One-time Top-Up credits and automatic hard stops at 402 make BETA usage easier to govern.
Trust signals for BETA review
The public site exposes the customer controls that matter without publishing internal implementation details.
- Canada
Gateway on GCP Montreal. - Privacy
Public policy, DPA and sub-processors. - Security
Responsible disclosure and security contact. - Transparency
Catalog, pricing and status are reviewable.
Pricing
Starter
$10 CAD
One-time Top-Up credit — never expires, usage-based billing.
Builder
$50 CAD
One-time Top-Up credit — never expires, usage-based billing.
Scaler
$200 CAD
One-time Top-Up credit — never expires, usage-based billing.
Pro
$500 CAD
One-time Top-Up credit — never expires, usage-based billing.
Free trial
25 000 tokens
One free trial per account, on deepseek-v4-flash.
See the billing guide → aiorouter.ca/docs/billing-guide
How We Compare
| Capability | AIOrouter | Generic model router | Direct provider API |
|---|---|---|---|
| Multi-model access | ✓ BETA catalog | ✓ Varies | - One provider |
| Pre-routing protection layer | ✓ Built in | - Not standard | - No |
| Data Residency | ✓ Canada | - Varies | - Provider-specific |
| CAD billing and budget controls | ✓ Subscription, caps, Top-Up | - Varies | - Varies |
| Trust documentation | ✓ Policy, DPA, status | - Varies | - Provider-specific |
| Per-token pricing | ✓ Provider-published public rates | ↑ 5–30% markup | ✓ Published rates |
Your key works with your favorite tools
Your AIOrouter API key is OpenAI-compatible (and /v1/messages for Claude) — it connects to any BYOK tool. You are never locked into one tool.
Desktop app + CLI (responses API)
All 19 models in the picker (config import)
OpenAI-compatible extensions
BYOK coding agent (OpenAI-compatible API)
VS Code agent with a custom endpoint
Via API (see the migration guide)
Native VS Code extension — coming soon
🔒 Secure checkout powered by Stripe — Visa · Mastercard · Amex · CAD · We never store your full card number.