• pricing •
One subscription,
every model.
No per-token bills. Your plan is metered in rolling 5-hour and weekly windows — pick the usage that fits, use the same account across the CLI, desktop and VS Code.
Free
Get started with RouterBench — a taste of every model.
- Every model, smart routing
- Rolling 5-hour + weekly limits
- CLI, desktop & VS Code — one sign-in
- Browser sign-in, no keys to manage
Pro
Generous all-day usage for individual developers.
- ~5× the Free usage windows
- Every model — no per-token bills
- All surfaces, one account
- Usage meter in every app (/plan)
Max
5× more usage for power users who never stop.
- ~5× the Pro usage windows
- Every model, highest limits
- Built for heavy, all-day coding
- Priority routing
Enterprise
For teams and companies — on your terms.
- Comped org plans · per-seat budgets
- SSO / SAML · RBAC · audit logs
- Guardrails & PII redaction
- On-prem / private deployment
billed monthly · in USD via Stripe · cancel anytime
• how it works •
Usage that just makes sense.
No token math, no surprise bills. Two rolling windows keep usage fair and predictable — the same way the best coding agents meter.
01 — rolling windows
5-hour & weekly
Your plan gives you a 5-hour and a weekly budget. Usage older than the window falls off automatically — heavier plans simply get bigger windows.
02 — every model
No per-token bills
Claude, GPT, Gemini and more — all included. You never think about token prices; the plan covers the model, whichever you pick.
03 — everywhere
One account
CLI, desktop and the VS Code extension share one sign-in and one subscription. Run /plan in any app to see exactly where you stand.
• enterprise •
AI at company scale, on your terms.
Comped organization plans with per-seat budgets, single sign-on, role-based access and audit logs — deployed in our cloud or fully on-prem. No public pricing; we scope it to your team.
- Comped org plans — one contract, every seat covered
- SSO / SAML · RBAC · audit logs
- Guardrails, PII redaction & model allow-lists
- On-prem / private deployment options
- Dedicated support & onboarding
• faq •
Pricing questions.
Start free, then subscribe to Pro or Max for a flat monthly plan with generous rolling 5-hour and weekly usage windows — no per-token bills, the plan covers every model. Enterprise is custom, billed per contract. Prefer pay-as-you-go? Top up credits and spend only when you route.
Yes — run it as managed cloud, inside your own VPC, or fully self-hosted and air-gapped with your own storage and models.
130+ models across OpenAI, Anthropic, Google, Groq, Moonshot, Z.ai, Sarvam and more — plus your own custom, fine-tuned or self-hosted endpoints.
Yes. Point the OpenAI SDK at api.routerbench.com/v1 and change one string — your existing apps, agents and tools keep working, and you get routing, observability and guardrails for free.
Install the CLI (npm i -g @routerbench.com/cli), the VS Code extension, or the desktop app. All of them route through routerbench/auto, so the right model handles every task.
The sensitivity firewall detects and tokenizes PII/PHI/secrets before any cloud hop; policy can force sensitive prompts to on-prem models so raw data never leaves your network.
Register any OpenAI/Anthropic-compatible endpoint (Ollama, vLLM, LM Studio, TGI) as a first-class provider, and the router picks it whenever it fits the task.
Yes. RouterBench is a model company and a first-party provider — we train models on real developer workflows and routing intelligence, serve them on our own infrastructure, and let them compete for every request under the same AI Credit Score™ as every other model.
Start free today.
Every model and smart routing on the free plan — sign in with your browser, no card required.