LLM router
An LLM router is software that decides, for each request, which large language model and which provider should answer it. It weighs quality, price, speed and company policy, using fixed rules or a classifier.
Why it matters for companies
Most steps of an AI agent are routine: reading files, summarizing, formatting. Sending those steps to a smaller model cuts cost, while the hard steps still get the strongest model.
A router also gives you a fallback. When one provider is slow or down, the request goes to another approved provider of the same model.
Example
A coding agent sends 1,000 requests in a working session. The router sends planning and difficult edits to Claude Opus and file reads and summaries to a small open model, so the bill drops while the hard steps keep the frontier model.
How Standard Compute handles it
A single API gives you frontier and open-source models, and it routes each step to the cheapest model that can do it and the cheapest provider fast enough to serve it.
If a provider goes down, your request fails over to another approved provider of the same model automatically, without leaving your region or provider rules.