# Samreshuuu Router

> A smaller AI bill without rewriting your code. Every model behind one key, simple requests 20× cheaper, hundreds of billions of tokens a month.

The router picks the best-value model for every request by price, speed and quality. One endpoint with fallback hosts, a log of every request and spend controls.

## Where the savings are

98% of requests don't need the most expensive model: of 311,060 model calls in the Samreshuuu app over the 14 days to 18.11.2026, the most expensive model was needed 4,880 times (1.57%). The router pays for a strong model only where nothing else will do.

- **Savings on autopilot.** New ways to save join the router as soon as they prove themselves. Your integration stays the same.
- **Smarter defaults.** We test new models on real work; the best one becomes the default.
- **Every model, one endpoint.** Text, images, video and speech from vetted hosts. If a host goes down, the request moves to the next one.

## Spend control

Spend is visible on the day of the call, and the statement arrives for the month.

- **Monthly cap:** the balance never spends more than the amount you set.
- **Auto top-up:** the balance tops itself up, so your product keeps running.
- **Request log:** the model, time and price of every call.
- **Invoice and statement:** top up by bank transfer, get a statement for the month.

## How we pick models

Every model is checked against independent benchmarks and our internal tests. The router gets the one that wins on quality (an overall task index: code, reasoning, knowledge), speed (how long the model takes to finish the task) and price (what the whole solved task costs). The top model is often several times pricier and slower with almost the same quality, so it is worth paying for only where the difference shows.

## Proven on Samreshuuu

The Samreshuuu app runs on this router every day: 336B tokens and 443K model calls in 30 days, 98% of requests without the most expensive model (as of 18.11.2026).

## Two lines of code

A new base URL and `"auto"` instead of a model name; the rest of your code stays the same. Works with the OpenAI SDK and any Chat Completions client; no subscription, calls are paid from the organization balance. Coding agents connect with one setting, and their spend lands in the same log.

## Questions

- **How does a company pay?** Top up the organization balance by invoice from a company account or by card. A statement arrives for each month.
- **Do I need a subscription?** No. You pay only for calls, with no minimum payment.
- **Will answer quality drop?** A cheaper model only gets what it can handle. Hard requests go to a strong one. If you need the same model every time, name it.
- **What do you store?** We don't write request or response text to the log: it holds the model, host, tokens and price.
- **How long does switching take?** A developer changes the base URL and the model name. Everything else stays as it was.

## Links

- Model API docs: https://samreshuuu.com/docs/model-api
- Models: https://samreshuuu.com/models
- App pricing: https://samreshuuu.com/pricing
