AI API Gateway

AI access, made governable.

Turn upstream model subscriptions into controlled, billable, observable API services with clean limits and no surprises.

Terminal
$ curl -X POST https://api.rabah.dev/v1/chat/completions \
  -H "Authorization: Bearer rk_live_..." \
  -d '{"model": "gpt-4", "messages": [...]}'

{
  "id": "chatcmpl-abc123",
  "usage": { "total_tokens": 42 },
  "cost": "$0.00126"
}
Capabilities

Everything needed to
operate AI access

One gateway. Clear limits. Full visibility.

Real-time monitoring

Track usage, latency, and cost with enough detail to catch drift before it becomes a billing problem.

Scoped access

Issue keys with model permissions, spending caps, and rate limits. One upstream account, many controlled surfaces.

Model routing

Route OpenAI, Claude, Gemini, and other providers through one stable interface with fallback behavior.

Usage ledger

Export clean records by user, model, time window, and project for reconciliation and resale billing.

How It Works

A clear path from
subscription to service

01

Connect

Add provider credentials for OpenAI, Anthropic, Google, and other upstream AI services.

02

Govern

Create scoped keys, rate limits, model permissions, and spending rules for every downstream user.

03

Operate

Route traffic, monitor usage, and reconcile cost from a single control plane.

Reliability

Built for teams
who measure everything

0
Uptime SLA
0
Average latency
0
API calls per day
0
Organizations
Ready

Bring your AI access under control.

Start small, route carefully, and scale once usage is visible.