Home › Docs
Get startedapicuts Documentation
apicuts is one API gateway for every major model that cuts your LLM costs by at least 20%, after our fee, without changing your models, speed or quality. These docs explain exactly how it works.
How it works
- Free teardown. In 15 minutes we size your avoidable spend from a usage export.
- Onboarding call. We set up your apicuts endpoint, key and data region (EU or US) with you.
- Change one line. Point your SDK's base URL at apicuts. See the quickstart.
- Watch the savings. Cost, savings, latency and quality show up live, per token, in your savings dashboard.
Why APICuts?
At least 20% lower all-in cost per request, after our fee, or you pay nothing. See pricing.
Change one base URL. Your prompts, tools and code stay the same. See the quickstart.
The lowest-cost route to a successful result, plus caching, batching, and prompt and output work. See routing.
If a provider errors or slows down, eligible requests move to a healthy route. See reliability.
Authorized providers only, prompts and outputs not stored by default, and an EU or US data region. See security.
Actual spend, baseline costs and realized savings, tracked per token, live. See the savings dashboard.
Every major provider, cloud platform and authorized inference platform, plus models you host. See where traffic goes.
Start here
Switch to apicuts in one line of code, and roll back in one line too.
Python, TypeScript, LangChain, LlamaIndex, the Vercel AI SDK and any OpenAI-compatible tool.
Cursor, Continue, Cline, Aider and other AI coding tools.
How every request takes the lowest-cost route to a successful result.
Every lever we use: caching, batching, prompt work, output limits and model routing.
Provider prompt caching and optional semantic caching.
What each status code means, and which errors to retry.
Keep spend predictable.
Actual spend, baseline costs and realized savings.
Failover, monitoring, SLAs and status.
What we keep, what we never keep, and where it runs.
How apicuts fits next to marketplaces, proxies and routers.
The guarantee
If your all-in cost per equivalent request, meaning your provider charges plus our fee, isn't at least 20% lower than the baseline we agree before go-live, you pay nothing. See pricing and our savings methodology.
Want us to find your 20%?
Book a free 15-minute API cost teardown. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.
Get a Free 15-Minute API Cost Teardown