Loading...
Loading...
OmegaEngine · Gateway
The AI Gateway acts as a policy-enforced proxy between your agents and LLM providers. Every request passes through OmegaEngine for real-time policy enforcement, cost tracking, and audit logging — with zero code changes.
Your agent sends a standard OpenAI-compatible request to the Gateway URL instead of the provider directly.
OmegaEngine evaluates the request against your tenant policies — checking cost limits, content rules, and rate quotas.
Approved requests are forwarded to the target model. The full decision is logged with 60+ audit signals.
Route to any major LLM through a single, unified API. Switch models without changing client code.
GPT-5.4, GPT-5.4 Mini, o3, o4-mini
Claude Opus 4.6, Sonnet, Haiku
Gemini 3.1 Pro, Flash, Ultra
Llama 4, Llama 3.3
Mistral Small 4, Devstral 2
Command R+, Embed v4
Replace your provider's base URL with the OmegaEngine Gateway. All calls now route through policy enforcement automatically.
import OpenAI from "openai";
// Point your existing client at the OmegaEngine Gateway
const client = new OpenAI({
baseURL: "https://gateway.omegaengine.ai/v1",
apiKey: process.env.OMEGA_API_KEY,
});
// Every call is now policy-enforced + audited
const response = await client.chat.completions.create({
model: "gpt-5.4",
messages: [{ role: "user", content: "Recommend an investment strategy" }],
});
// Response includes OmegaEngine headers:
// x-omega-decision-id, x-omega-risk-score, x-omega-policy-outcomeEvery request is evaluated against your tenant policies before reaching the model. Block, allow, or escalate to human review.
Real-time token counting and budget limits per tenant, team, or agent. Get alerts before you hit limits.
Per-key, per-tenant, and per-model rate limits. Smooth traffic spikes without provider throttling.
Every proxied request is logged with 60+ signals — input hash, risk score, policy outcome, latency, cost.
If a model is down or rate-limited, the Gateway automatically retries with your configured fallback model.
Tenant API keys never touch the provider. OmegaEngine injects provider credentials server-side.
Every proxied response includes OmegaEngine metadata headers for observability:
| Header | Description | Example |
|---|---|---|
| x-omega-decision-id | Unique audit trail ID | dec_a1b2c3d4 |
| x-omega-risk-score | Risk score (0–1) | 0.42 |
| x-omega-policy-outcome | Policy result | ALLOW | REVIEW | BLOCK |
| x-omega-cost-usd | Estimated request cost | 0.0032 |
| x-omega-latency-ms | Gateway overhead | 12 |