Route every AI prompt
to the right model.
One drop-in endpoint for every LLM provider. routeur.ai routes each request to the lowest-cost model — with prompt shielding, DLP and policy controls built in — cutting AI costs by ~20% without touching your business logic.
api.routeur.ai/v1
routing engine
Features
One control plane for production LLM traffic
Route requests, enforce policy, cap spend, trace decisions, and add fail over providers without rewriting application code.
Intelligent Routing
Define priority-based rules in a visual editor. Route by prompt length, keyword, route name, or custom headers — first match wins, no code deploys needed.
Full Observability
Every request logged: provider, model, tokens in/out, latency, and exact cost. See precisely where your AI spend is going, down to each individual call.
Cost Control
Set spend budgets per team or project with real-time alerts. Detailed reports show your savings versus going direct — the payoff is immediate and measurable.
Prompt Shields
Automatically block prompt injection, jailbreak attempts, and policy violations before they reach your providers — protecting your system prompts and your users.
Data Protection
DLP scanning strips PII — names, emails, card numbers — before prompts reach upstream model providers. Stay compliant without modifying a single line of application code.
Quality & Anomaly Detection
Monitor response quality scores, detect anomalous usage patterns, and filter harmful content before it reaches your users — all configurable from the dashboard.
Integration
Up and running in minutes
routeur.ai is OpenAI-compatible. Drop it in without rewriting your application — just point your existing client at our endpoint.
Connect your providers
Add your OpenAI, Gemini, DeepSeek, and Anthropic API keys in the dashboard. We encrypt them at rest and you never expose them in your app code again.
Change two lines of code
Point your OpenAI client at api.routeur.ai/v1. No new SDK. No new library. Your business logic stays byte-for-byte identical.
from openai import OpenAI
client = OpenAI(
api_key="sk-your-openai-key"
)from openai import OpenAI
client = OpenAI(
api_key="rtr-your-routeur-key",
base_url="https://api.routeur.ai/v1"
)Configure routing rules
Use the visual rule editor to define which prompts go where. Set priorities, test live, and deploy instantly — no code deploys, no restarts, no engineering tickets.
Dashboard
Command centre for your AI spend
Real-time visibility into every request, every provider, every penny.
| Time | Route | Provider · model | Cost | Latency | Shield | Status |
|---|---|---|---|---|---|---|
| 14:03:21 | auto | OpenAI gpt-4o-mini | $0.0021 | 312 ms | pass | 200 |
| 14:03:18 | auto | Google gemini-flash | $0.0008 | 198 ms | pass | 200 |
| 14:03:15 | pinned | OpenAI gpt-4o | $0.0261 | 1.2 s | dlp | 200 |
| 14:03:11 | auto | DeepSeek deepseek-chat | $0.0004 | 421 ms | pass | 200 |
Security & compliance
Enterprise AI safety,
built in — not bolted on.
Every request flows through multiple security layers before reaching a provider, and again on the way back.
-
Prompt Shields
Block injection attacks, jailbreaks, and policy violations before they reach your LLM providers.
-
Data Loss Prevention
Automatically detect and mask PII — names, emails, credentials, card numbers — in every prompt.
-
Output Moderation
Filter harmful, toxic, or off-brand content from responses before they reach your users.
-
Anomaly Detection
Get alerted when usage deviates — cost spikes, unusually long prompts, or suspicious access patterns.
Pricing
Transparent pricing
for production AI
Every plan includes intelligent routing, observability, and built-in security controls from day one. Scale with seats and routed usage as your platform grows — no hidden platform fees, no surprise feature gates.
Transparent seat-based pricing with scalable usage allowances. Beta customers lock in their price permanently.
For teams exploring AI routing and reducing LLM spend.
- Smart provider & model routing
- Automatic failover & retries
- Cost & latency analytics
- Prompt injection protection
- DLP & PII masking
For teams running production AI workloads that need visibility, governance and cost control.
- Includes everything in Starter
- Advanced routing conditions
- Team & project isolation
- Spend budgets & alerts
- SAML SSO
- Priority email support
For organisations operating AI across multiple teams, regions and regulated environments.
- Includes everything in Pro
- 99.9% SLA-backed uptime
- SLA & compliance options
- SCIM provisioning
- Extended audit log retention
- SIEM & compliance integrations
- Dedicated onboarding & support
Need the detail? Compare every feature, limit and add-on price →