Your first $5 becomes $15Get started

The NemoRouter Blog

Notes on shipping reliable LLM infrastructure.

Engineering, product, and company posts from the NemoRouter team. What we shipped, why we built it that way, and the trade-offs we made along the way. Code-first, cost-honest, no vendor-marketing fluff.

Browse all postsBrowse by tag
01
Product
Features & releases·9
02
Engineering
Architecture & internals·13
03
Comparison
How we compare·13
04
Guides
How-tos & best practice·16
All posts

Browse the catalog

Filter by category, or browse the full archive of deep-dives.

63 posts found
Budgets vs Rate Limits: Which Control to Reach For
Guides

Budgets vs Rate Limits: Which Control to Reach For

Both return 429, but they solve different problems. Here is a decision guide for when to use a budget cap, when to use a rate limit, and why you almost always want both.

Nemo Team
7 min
What to Log (and Not Log) on an LLM Gateway
Guides

What to Log (and Not Log) on an LLM Gateway

Request logs are your debugger and your liability at once. Here is a practical policy for LLM logging — what to capture, what to redact, how long to keep it, and the four logging levels to choose from.

Nemo Team
8 min
Measuring Real LLM Latency: p50, p95, and p99
Engineering

Measuring Real LLM Latency: p50, p95, and p99

An average latency number hides the requests that ruin your UX. Here is how to measure LLM latency with percentiles, why p95/p99 matter more than the mean, and how to read tail latency on a gateway.

Nemo Team
9 min
Gateway Credits vs Prepaid Tokens: What's the Difference
Guides

Gateway Credits vs Prepaid Tokens: What's the Difference

Provider prepaid tokens lock you to one model''s pricing. Gateway credits are model-agnostic dollars. Here is how the two differ and why credits fit a multi-model world better.

Nemo Team
7 min
Setting Up Auto-Topup Without Surprise Bills
Guides

Setting Up Auto-Topup Without Surprise Bills

Auto-topup keeps your gateway from running dry mid-traffic — but done wrong it's an uncapped spend loop. Here is how to configure it with a ceiling so it helps without becoming a runaway.

Nemo Team
7 min
Attribute LLM Spend by Team, Customer, and Feature
Guides

Attribute LLM Spend by Team, Customer, and Feature

"The AI bill went up" is useless without attribution. Here is how request tags let you slice LLM spend by team, customer, feature, and environment on a gateway — no per-call bookkeeping in your app.

Nemo Team
8 min
Why We're Managed, Not a Self-Hosted Gateway
Company

Why We're Managed, Not a Self-Hosted Gateway

You could run your own LLM gateway. We chose to run it for you instead. Here is the reasoning — and when self-hosting is genuinely the right call.

Nemo Team
7 min
Platform Fee, Not Feature Gating
Company

Platform Fee, Not Feature Gating

Most SaaS hides its best features behind the top tier. We unlock every feature on every tier and differentiate on a platform fee instead. Here is why that bet is better for customers and for us.

Nemo Team
7 min
What Is an LLM Gateway? A 2026 Primer
Guides

What Is an LLM Gateway? A 2026 Primer

An LLM gateway is a single endpoint that routes to every model provider while handling keys, cost, rate limits, and safety. Here is what it does, when you need one, and how to evaluate it.

Nemo Team
8 min

Stay in the loop

Get every new post by email

One email when a post lands — no digests, no marketing, no tracking pixels. Or wire it into your reader with the RSS feed.

Subscribe by emailRSS feed

Atom + RSS available · unsubscribe one-click