Routing
apicuts sends every request on the route that gives you the lowest cost for a successful, quality-approved result. Not the cheapest token price: the cheapest task that actually works.
The rule: lowest cost per successful task
A cheaper model that fails, retries or produces worse output costs more than a stronger one that gets it right the first time. So we measure the cost of the whole task, including retries and follow-up calls, and route to whatever is cheapest at the quality you need.
Provider routing
For the model you ask for, apicuts picks among verified, authorized providers using:
- Effective price, including cached-token discounts, not just list price.
- Cache affinity, so requests that share a prompt prefix keep hitting the provider that holds the cache.
- Latency and throughput, so you keep the same speed.
- Error rates and capacity, so traffic avoids providers that are struggling.
Same model, same output quality. Supported OpenAI and Anthropic models appear via authenticated GET /v1/models and in /app/integrate (or preview /demo/models; native Gemini and OpenAI /v1/responses expansion are tracked on the roadmap).
Load balancing & failover roadmap
Today each protocol routes to configured authorized upstream capacity while preserving prompt-cache affinity; automated cross-provider failover, health-weighted load balancing, and self-serve routing policy rules are under Next on the roadmap.
Optional model routing
Some requests don't need your largest model. With your approval during a 360° cost audit, we test lower-cost equivalent models against your own evaluations first, roll them out to a small share of traffic, and only then send simple requests their way. Complex requests stay on the stronger model. Nothing switches models without your sign-off.
Your routing rules and keys
Sign up and scope company keys in /app/keys to control which models and endpoints an app or team can call, with privacy guarantees detailed in security and privacy. Custom routing recommendations, latency targets, and candidate model substitutions can be tuned alongside a free 360° Cost Report or via [email protected].
Want us to find your 20%+?
Get a free 360° cost report. Bring last month's provider usage and we'll show you your biggest waste and the first fix we'd ship.
Get a Free 360° Cost Report