Browse documentation

Why nRouter

Access all major LLM providers through a unified API key, featuring enterprise budget controls, audit logging, guardrails, and multi-tenant isolation.

nRouter is the enterprise LLM gateway between your app and every major model provider — one OpenAI-compatible API with pre-call budget holds, in-path guardrails, and multi-tenant isolation at a 0% platform fee.

  • One key, one bill: Call OpenAI, Anthropic, Google Vertex AI, Azure Foundry, and Alibaba US with one NROUTER_API_KEY (Quick Start · Auth).
  • Spend you can trust: Pre-call reserve+settle billing at exact list prices (x-nr-request-cost), card fees absorbed, and org → team → key RPM/TPM and spend caps (Budgets).
  • Zero-spend guardrails: PII redaction, prompt-injection defense, and content moderation run in-path before the provider call — blocked requests spend $0 (Guardrails).
  • Strict isolation: Row-level tenant isolation, organization roles (owner, org_admin, member, viewer) plus team-scoped team_admin authority, CSV log exports, and Enterprise SSO + SCIM (Organizations · Teams).

How we compare

CapabilitynRouterOpenRouterPortkeyHelicone
Platform & card fees0% (absorbed)fee appliesper planper event
Automatic routingDecision model per requestround-robinrules-basedobs-only
Pre-call holds & guardrails✓ ($0 on block)—paidobs-only
Exact list-price settlement✓ (x-nr-request-cost)post-paidpost-paidpost-paid

Compare: OpenRouter · Portkey · Helicone · Vercel AI Gateway · Migration Guide

Get started

Start building with nRouter

One API key, three steps. Choose your tool to begin.

  1. Set your API key

    export NROUTER_API_KEY="<YOUR_API_KEY>"
  2. Configure Claude Code

    Choose a tool, then copy its setup from the panel.

npm install -g @anthropic-ai/claude-code
Claude Code · gpt-5.4-mini
# Point Claude Code to nRouter gateway
export ANTHROPIC_BASE_URL="https://api.nrouter.ai"
export ANTHROPIC_API_KEY="$NROUTER_API_KEY"

# Launch with gpt-5.4-mini
claude --model gpt-5.4-mini
Was this page helpful?