Route by cost, latency, or weight. Fall back when a model fails.
- Fallback chains
- Model aliases
Enterprise LLM Gateway
Every model. One API key.
Sub-millisecond LLM gateway with smart routing, AI guardrails, and real-time cost controls — for your teams and your agents.
import { nRouter } from "@nrouter_ai/sdk"
const client = new nRouter({
model: "deepseek-v4-pro",
})
console.log("Running nRouter agent...")
const stream = await client.chat.create({
model: "deepseek-v4-pro",
messages: [
{ role: "user", content: "Explain Tokio SIMD" }
],
stream: true,
})
for await (const chunk of stream) {
process.stdout.write(chunk.content)
}
console.log("Done")Your AI stack, unified.
Scrolling pauses while you hover over or focus this strip.
Architecture
Every request runs through one gateway.
Every call clears the AI Security layer first: WAF, DDoS shielding, rate limits, and per-org budgets. Then your routing policies apply.
Your apps
- Chat apps
- Agents
- RAG
- SDKs
sk-nrouter-••••one key
AI Security
- WAF
- DDoS
- Rate limits
- Budgets
- GuardrailsPII + injection, in & out
- Smart routingYour routing strategy
- Budgets & creditsEnforced spending limits
- Semantic cacheDedupe repeat prompts
- FallbacksRetry across providers
- ObservabilityLogs, traces, spend
Every provider
Azure Foundry
Alibaba US
Google Vertex AI
Anthropic
OpenAI
AWS Bedrock
Multi-providermodels · one bill
Your apps use one nRouter key. We manage the provider credentials.
Platform
Everything you need. Nothing you don't
Gateway, guardrails, routing, and budgets. One platform for production AI.
SDKs & Frameworks
Use the stack you already know.
Install a published nRouter SDK or keep your existing OpenAI-compatible client and change the base URL.
Python
Published on PyPI
pip install nrouter-sdk
TypeScript
Published on npm
npm install @nrouter_ai/sdk
Swift / iOS
Swift Package Manager
.package(url: "https://github.com/nRouterAI/nrouter-sdk.git", from: "2.2.1")
Go
Published on pkg.go.dev
go get github.com/nRouterAI/nrouter-sdk/sdks/go/v2@v2.2.1
Java
Published on Maven Central
implementation("ai.nrouter:nrouter-sdk:2.2.1")
K
Kotlin
Published on Maven Central
implementation("ai.nrouter:nrouter-sdk-kotlin:2.2.1")
Android
Published on Maven Central
implementation("ai.nrouter:nrouter-sdk-android:2.2.1")
Dart / Flutter
Published on pub.dev
dart pub add nrouter
REST API
OpenAI-compatible HTTP
https://api.nrouter.ai/v1/chat/completions
R
Published on R-universe
install.packages("nrouter", repos = "https://nrouterai.r-universe.dev")
Model Marketplace
Choose your model, one API.
Browse live models and pricing. Use them with one nRouter key.
0 models displayed
Proven at Scale
Trusted by engineering leaders worldwide
From high-concurrency live sports to sovereign banking AI, see why leading teams deploy production LLMs on nRouter.
< 2msP99 LATENCYLive Sports & Media
“nRouter handles our peak playoff traffic with automated cross-cloud failover and sub-millisecond overhead. Zero dropped fan requests during game-ending buzzer beaters.”
Marcus Vance
VP of Platform Architecture · NBA Sports Tech
500M+SECURE INTERACTIONSBanking & Gov
“With real-time inline PII redaction and sovereign data boundaries, nRouter lets our engineering teams deploy LLMs at national scale while exceeding regulatory audits.”
Sunil Mehta
Head of Enterprise AI Governance · SBI
4.2xTHROUGHPUT BOOSTEdTech Platform
“Swapping models and setting per-student rate limits took two lines of code. Our unit costs dropped 38% while throughput quadrupled across global learners.”
Elena Rostova
Principal AI Engineer · Brainly
100%BUDGET CAP ENFORCEDAgentic Infrastructure
“The virtual key architecture and pre-call budget reservation completely eliminated runaway LLM spend and unexpected bill shock for our agent fleet.”
Suman Kanuganti
CEO & Founder · Personal AI
12M+TICKETS RESOLVEDCustomer AI Agents
“nRouter handles our automated customer service agents with zero-downtime failover between Claude and GPT. Our enterprise SLAs are consistently met at 99.99%.”
Jesse Zhang
CEO & Co-Founder · Decagon AI
< 5msROUTING LATENCYEnterprise Search
“Smart routing across multi-modal embedding models cut our inference costs by 45% while keeping search latency under 5ms worldwide without vendor lock-in.”
Arjun Sethi
VP of Engineering · Percept Labs