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.
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.
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.
Coding agents burst into hundreds of model calls per task across many tools. Here is how a gateway gives them budgets, fallback, and per-task attribution so an autonomous loop can't run up a surprise bill.
4% Markup
0% Tier 3
Before an LLM call leaves the gateway it clears four independent limits: credit balance, budget cap, rate limit, and guardrails. Here is what each one checks and why they are separate.
A runaway agent or leaked key can burn thousands in hours. Here is how hard budget caps, soft alerts, and reserve-and-settle stop the bleeding on an LLM gateway — before the invoice arrives.