Ingate Documentation
Everything you need to integrate, configure, and operate the Ingate AI gateway.
New to Ingate?
Get your first LLM request routed through Ingate in under 5 minutes.
Go to Quickstart →What Ingate Does
Ingate is a fully managed cloud AI gateway that sits between your applications and LLM providers. Change one URL, keep all your existing code. Ingate auto-detects the target provider from the request path. OpenAI, Anthropic, Azure, Ollama, and others work out of the box with zero configuration.
Unlike SDK-based observability tools that require code instrumentation, Ingate operates at the network layer as a transparent proxy. You get full observability, prompt management, an eval engine with datasets and a comparison playground, provider fallback, and enterprise security governance, all without touching your application code.
Transparent Proxy
Auto-detects provider from request path with no headers needed for OpenAI, Anthropic, Azure, or Ollama. Sub-millisecond overhead with full SSE streaming.
Full Observability
Every request logged with cost tracking, token usage, latency metrics, and session/user attribution across all providers.
Prompt Registry
Version-controlled prompt templates with namespace organization, rollback, and environment promotion.
Eval Engine & Datasets
Built-in evaluators, versioned test datasets, and a playground with side-by-side model comparison mode.
Multi-Tenancy & RBAC
Organizations, teams, apps, scoped API keys, and role-based access control for every resource.
Enterprise Security
Guardrails, audit logs, budget controls, webhooks, bring-your-own-storage, PII redaction, and response caching.
Architecture
Your App / Agent → Ingate Cloud → OpenAI / Anthropic / Azure / Ollama
↓
Logs · Evals · Prompts · Sessions · DashboardIngate Cloud runs at api.ingateai.com. Your dashboard lives at app.ingateai.com. There is nothing to deploy or self-host. point your base URL at Ingate and you're live.
Integration Example
The simplest integration is a single line change. Ingate auto-detects that requests to /v1/chat/completions go to OpenAI, so no provider header is needed:
// Before: direct to OpenAI
const client = new OpenAI({ apiKey: "sk-..." });
// After: route through Ingate (one line change)
const client = new OpenAI({
baseURL: "https://api.ingateai.com/v1",
apiKey: "sk-ingate-your-key",
});
// That's it. Your existing code works unchanged.
// Ingate auto-detects OpenAI from the /v1/... path.Works with any provider
Anthropic, Azure, Ollama, and other providers are auto-detected the same way. For providers Ingate doesn't recognize, add an X-Ingate-Provider header. See Providers for the full list.
Coding Agents
Ingate works as the gateway for coding agents like Claude Code, Cursor, Aider, and Continue. Point the agent's base URL at Ingate and every request is automatically logged with full session attribution. No plugins or custom middleware required.
# Claude Code: set your base URL
export ANTHROPIC_BASE_URL="https://api.ingateai.com"
export ANTHROPIC_API_KEY="sk-ingate-your-key"
# Cursor / Aider / any OpenAI-compatible agent
export OPENAI_BASE_URL="https://api.ingateai.com/v1"
export OPENAI_API_KEY="sk-ingate-your-key"Ingate auto-detects the provider from the request path, so agents work without any extra configuration. Every request shows up in your dashboard with cost, latency, and token usage.