Blog

Research on AI API gateways — how they actually charge, what the models really cost per million tokens, and which levers move an LLM bill. Every figure we publish is dated and sourced.

The AI gateway markup war is over. The fight moved to platform fees

Every major gateway now passes tokens through at 0% markup — the money moved to platform fees. At 50M requests/month the spread runs from free (Cloudflare) to $10,300 (Kong), all on identical token cost. Plus Envoy AI Gateway’s v1.0 GA, and the benchmark everyone quoted that turns out to be a mock.

AI API gateways in 2026: how they work, what they really cost, and when to skip them

A gateway with “0% markup” can still take 16% of a small top-up. The biggest savings in 2026 are not the gateway at all — they are 90% off cached input and 50% off batch, published by the model vendors themselves.

Claude API pricing in 2026: the complete cost breakdown

Every price, every multiplier, every trap — including the one Anthropic states but nobody budgets for: newer models produce ~30% more tokens for the same text, and up to 47% on technical English.

GPT-5.5 vs Claude Opus 4.8 vs Gemini 3.1 Pro: which is actually cheapest?

Two of these models cost the same per token. One costs nearly twice as much to run. Measured on the identical benchmark suite: Opus 4.8 $4,011, GPT-5.5 $2,159, Gemini 3.1 Pro $815.

How much does it cost to run an AI agent? A real invoice, broken down

$13 per developer per day, 3,500× the tokens of a chat call, and one documented $12 API call where 21 million cache-read tokens were billed for 4,000 tokens of real input.

Prompt caching explained: how to get up to 90% off your input tokens

One team went from a 7% cache hit rate to 84% and cut LLM cost 59%. The change that did most of it? Moving a timestamp out of the system prompt. Every vendor’s rules, and why caches silently miss.

OpenRouter vs LiteLLM: managed gateway or self-hosted proxy?

They are not rivals — one sells tokens, the other is software you run. OpenRouter publishes its own break-even: self-hosting wins above $3,600/month of spend. Add an engineer and it moves to $36,400.

OpenRouter alternatives in 2026: the honest comparison

People leave over the 2026 403 wave, not the fee. Verified pricing for 14 alternatives — 5% on tokens, 5.5% on top-ups, $49 per 100k logs, or genuinely zero markup.

More articles are on the way. We publish only when we have numbers worth publishing.
Best AI Gateways

Copyright © 2026 Best AI Gateways

Independent ranking. We may be rewarded for recommending the service we rate best and sending users to it — that reward pays for the research behind this comparison and never buys a ranking position, at no extra cost to you. Information is provided “as is” without warranty. See our Disclaimer & Terms.