Optimize your agent for cost and performance — with every run.
An open-source LLM router that sends routine calls to open models and pays frontier prices only for the calls that earn them. Zero harness changes.
curl -fsSL https://bitrouter.ai/install.sh | shWhere agent runs lose cost and performance.
Four leaks in every long, autonomous run — each one fixed by a mechanism below.
A blip at file 140 shouldn't kill the run.
Your agent is 140 files into a long run when a provider rate-limits it, and the run dies. You pay for those 140 files again on the retry — every long agent loop breaks the same way, one blip back to zero.
- └Overnight jobs that finish
- └No babysitting rate limits
- └The agent never sees the failure
You're billed per run. Can you see per run?
Stack a few agents and providers and the logs turn to noise. You see the bill, but not which agent, which model, or which hop ran it up — so you can't cut it.
- └Which agent, which model, which step
- └Cost per run — not per month
- └Replay the exact call chain
An agent with your keys is an attack surface.
An autonomous agent reads untrusted input, holds your credentials, and emits whatever it's told. One injected run can leak a secret or burn the budget — the cheap, fast pipeline you built is only as safe as its worst run.
- └Prompt injection slips through
- └Secrets leak in outputs
- └One agent, unbounded spend
Always-opus is a budget leak.
Most calls in a run are trivial — a lookup, a format, a yes/no. Bill every one of them at frontier prices and the cost compounds across thousands of runs.
- └Routine calls an open model could handle
- └No price-aware routing
- └Cost you find out about later
Why agents run on BitRouter.
Four mechanisms, one for each leak above. One job: optimize every agent run for cost and performance.
A dead run is a run you pay twice for.
Reroutes across providers mid-run, transparently — so a rate-limit at file 140 never makes you re-pay for 139 files of work.
Billed per run. Now visible per run.
Every agent, every model, every hop — with cost and latency attributed to the run, not smeared across a monthly invoice.
Cheap and fast means nothing if it leaks — or runs away.
One policy at the router — injection and output filtering, private by default, and per-agent spend and loop caps that stop a runaway before it drains the key.
Pay open-source prices for the calls that don't need frontier.
Matches each call to the cheapest model that can do it — open models for the routine 90%, frontier reserved for the hard calls.
Questions before you ship.
Common questions about pricing, routing, and data handling. If yours isn't here, check the docs or talk to us — we usually reply within a day.
Start routing in under a minute.
One API key, every model. No monthly fees, no lock-in. Self-host or use the hosted edge.
curl -fsSL https://bitrouter.ai/install.sh | sh