Question 1

What is Nemo Router?

Accepted Answer

Nemo Router is a managed LLM gateway that gives teams one API key to access 200+ AI models from OpenAI, Anthropic, Google, Mistral, Meta, and more. It is OpenAI-compatible, includes built-in guardrails, real-time cost tracking, team management, and a 0% platform fee for the first 100,000 founding customers.

Question 2

How is Nemo Router different from a public LLM gateway?

Accepted Answer

Nemo Router is purpose-built for teams, not individual developers. It combines the one-key-many-models experience of a public gateway with enterprise features that teams normally only get from self-hosted proxies: per-team budgets, org-wide RBAC, guardrails scoped per key, prompt management, and audit logs. All features are unlocked on every tier — plans only affect the platform fee (0% / 2% / 4%) and guaranteed RPM/TPM.

Question 3

What is the platform fee?

Accepted Answer

Nemo Router charges a platform fee on top of provider costs: 4% on the Starter tier, 2% on Team, and 0% on Business. The 0% fee is locked for life for the first 100,000 founding customers (offer ends August 2026). You always pay the full model price to the provider — the platform fee is separate and transparent.

Question 4

Which AI models does Nemo Router support?

Accepted Answer

Nemo Router supports 200+ models across 15+ providers including OpenAI (GPT-4o, GPT-5.3, o1), Anthropic (Claude Opus 4, Sonnet 4, Haiku), Google (Gemini 2.5 Pro, Flash), DeepSeek, Mistral, Meta Llama, AWS Bedrock (Amazon Nova), Cohere, and more. New models are added within days of general availability.

Question 5

Is Nemo Router OpenAI-compatible?

Accepted Answer

Yes. Nemo Router exposes an OpenAI-compatible REST API at https://api.nemorouter.com. Existing code using the OpenAI SDK works by changing two lines: the base URL and the API key. All features (routing, guardrails, observability, budgets) work through the standard chat completions endpoint — no custom SDK required.

Question 6

How does cost tracking work?

Accepted Answer

Every request is settled at Nemo Router using the canonical cost computed by LiteLLM, which reads the upstream provider cost header (x-litellm-response-cost) and charges your credit balance. You get per-request, per-model, per-team, and per-key cost breakdowns in real time via the dashboard and the /usage endpoint. Budgets can be enforced at any of those scopes and trigger 429s when exceeded.

Question 7

What guardrails does Nemo Router provide?

Accepted Answer

Nemo Router runs pre-call, during-call, and post-call guardrails from providers like Aporia, Guardrails AI, Bedrock Guardrails, Azure Content Safety, and Lasso. Guardrails are configured per key, per team, or per org. All providers are unlocked on every plan — you do not need to upgrade to enable safety controls.

Feature	Nemo Router	OpenRouter	LiteLLM Enterprise
Pricing Model	Credits, 0–4% fee	5–15% markup	Annual license
Managed Infrastructure	Included	Included	You operate
All Features Unlocked	Every tier	Limited	Paid tier only
Team & Org Management	Included	No	Included
Guardrails & Safety	Built-in	No	Add-on
Budget Controls	Per key / team / org	Basic	Paid tier only
Audit Logging	Included	No	Paid tier only
OpenAI-Compatible API	Yes	Yes	Yes
Setup Time	Sign up & call	Sign up & call	Provision, deploy, operate

The Intelligent Backbone
for Multi-Model AI.

Every model. One API.

GPT-4o

Claude Opus 4

Gemini 2.5 Pro

DeepSeek V3

Mistral Large

Amazon Nova Pro

Claude Sonnet 4

GPT-5.3

Everything you need. Nothing you don't.

Smart Routing

Guardrails

One API Key

Spend Tracking

Budget Controls

Prompt Templates

Team Management

Observability

Model Catalog

Why teams choose Nemo Router.

One API key.
Every model. Zero fee.

The Intelligent Backbonefor Multi-Model AI.