NemoRouter Launches Managed LLM Gateway with Every Enterprise Feature on Every Tier
NemoRouter is publicly available — a managed LLM gateway providing one API key, one bill, and every governance feature (guardrails, audit logs, budgets, A/B testing) unlocked on every tier. Built on the open-source LiteLLM proxy. 4% / 2% / 0% platform-fee tiers undercut public-gateway norms.
SUNNYVALE, CA, May 5, 2026 — NemoRouter, a managed LLM gateway built by CloudAct Inc. on the open-source LiteLLM proxy, is publicly available today. The platform gives engineering teams unified access to AI models across providers through a single API key, with the multi-tenancy, billing, and governance layer that production workloads require.
One key, one bill, every feature on every tier
Most LLM gateways gate enterprise features — SSO, audit logs, guardrails, team management — behind paid tiers. NemoRouter does the opposite. Every feature is unlocked on every plan from day one. Tiers vary the platform fee charged on top of provider cost, not the feature set.
- Tier 1 — PAYG: 4% platform fee. $5 free credits on signup, no card required.
- Tier 2 — Monthly: $100/mo minimum credit purchase, 2% platform fee.
- Tier 3 — Annual: $1,200/yr minimum credit purchase, 0% platform fee.
- Enterprise: Custom pricing, 0% platform fee, dedicated capacity, custom SLA.
The 0% Tier 3 platform fee is a deliberate undercut of public LLM gateways that typically charge 5–15% markup. Every dollar a customer commits goes to credits — the platform fee is charged on top, never deducted.
At-launch capabilities
- 18 models live at launch across Google Vertex AI (Gemini, Imagen, Veo, embeddings); OpenAI, Anthropic, AWS Bedrock, Azure OpenAI, Cohere, Mistral, and Meta integrations expanding weekly.
- AI guardrails on every request — PII redaction (Microsoft Presidio), prompt-injection detection, secret scanning, abuse blocking, response scanning. Included on every tier.
- Smart routing — usage / latency / cost-based routing strategies, fallback chains across backup models, configurable retries and cooldowns.
- Prompt management — server-side templates with versioning, A/B testing, Jinja2 variables.
- Team management — Owner / Admin / Member / Viewer RBAC, per-team and per-virtual-key budgets, single-org-per-user invitation flow.
- Observability — request logs, logging callbacks (Langfuse, Datadog, S3, Slack), per-org data policy from zero-logging to PII-redacted.
- Security architecture — Postgres Row-Level Security on every tenant table, hashed virtual keys, master-key isolation, TLS 1.2+ / AES-256 encryption, immutable audit trail.
- Compliance posture — SOC 2-aligned and ISO 27001-aligned controls (active); GDPR-compliant; HIPAA-eligible with BAA on Enterprise. Underlying infrastructure (Cloud Run, Supabase) is SOC 2 Type II certified.
Why now
AI adoption is moving from experimentation to production. Engineering teams managing API keys, billing accounts, and integration code across multiple providers spend weeks on infrastructure work that doesn't differentiate their product. NemoRouter handles provider complexity, enforces governance at the gateway, and reports cost the same way regardless of which model the request hits.
About NemoRouter
NemoRouter is a product of CloudAct Inc., headquartered in Sunnyvale, California. The platform is built by founder Rama Surasani on the open-source LiteLLM proxy core, with NemoRouter contributing fixes and improvements upstream rather than maintaining a fork.
For media inquiries: press@nemorouter.ai. For sales: sales@nemorouter.ai. For security and compliance: security@nemorouter.ai.