Built for developers
burning Opus-priced tokens.

Phase-aware routing for AI coding agents. Planning goes to Opus; test generation goes to DeepSeek. You pay for the value — not for routing trivial code formatting at Opus rates.

Typical users cut their Cursor / Claude Code / Aider bill by 70–90%.
Want to pick models yourself? Try Direct mode — pay-as-you-go at list × 1.15, $5 free to start.
Free Trial
2 days, no credit card
Free · 2-day trial
Tokens1M tokens
Opus quotaNo Opus (Pro+ only)
Rate limit60 req/min
API keys2
  • Full phase-aware routing
  • All 15+ coding models
  • Dashboard + cost analytics
  • Expires after 2 days
  • After trial: upgrade or add BYOK keys to continue
Start free
Starter
Side projects, occasional agent use
$19 /mo
Tokens2M tokens
Opus quota50K Opus tokens
Rate limit100 req/min
API keys3
  • Phase-aware routing
  • All coding models
  • +15% overage, $40/mo cap
  • Email support
Start Starter
Solo
Full-time indie dev using agents daily
$29 /mo
Tokens5M tokens
Opus quota100K Opus tokens
Rate limit200 req/min
API keys5
  • Phase-aware routing
  • All coding models
  • +15% overage, $60/mo cap
  • Email support
  • Model-selection transparency headers
Start Solo
Studio
Small studios and contractors — name keys per engineer
$179 /mo
Tokens50M tokens
Opus quota800K Opus tokens
Rate limit1200 req/min
API keys20
  • Everything in Pro
  • Up to 20 API keys
  • Explicit model pinning allowed
  • +15% overage, $400/mo cap
  • Per-project cost breakdown
Start Studio
Team
Engineering teams — one key per engineer + CI keys
$299 /mo
Tokens80M tokens
Opus quota1M Opus tokens
Rate limit2400 req/min
API keys50
  • Everything in Studio
  • Up to 50 API keys
  • Shared dashboards
  • +15% overage, $600/mo cap
  • Dedicated Slack / onboarding
Start Team
Need more than 80M tokens / 50 API keys? Contact us for Enterprise — volume discount, SLA, region selection.

How billing works — no surprises

Included tokens

Each plan includes a generous monthly quota, sized for real coding-agent workloads. Opus has its own separate quota so high-cost planning calls don't drain your main budget.

Overage at list + 15%

Go over your quota? You're billed at the provider's public list price plus 15% — verifiable on each provider's pricing page, never inflated. Each plan has a default monthly cap so you'll never see a runaway bill; raise it in settings if you need more.

Top-ups or BYOK

Buy a one-time token pack if you prefer predictable bills, or bring your own provider keys (BYOK) and pay only the platform fee. Your call.

Plan comparison

All plans include phase-aware routing, all 15+ coding models, streaming, auto-failover, and the routing-decision response headers (X-CodeRouter-Phase).

FeatureStarterSoloProStudioTeam
Monthly price$19$29$99$179$299
Included tokens2M5M30M50M80M
Included Opus tokens50K100K500K800K1M
Rate limit (rpm)1002006001,2002,400
API keys35102050
Overage (+15% on provider list price)
Monthly overage cap$40$60$200$400$600
Top-ups (pay-as-you-go)
Opus top-up
Shared team dashboards
SupportEmailEmailPriorityPriorityDedicated

FAQ

What counts as a "token"?

Same as every provider — roughly 3–4 English characters, or ~0.75 words. A typical 10K-line code base as context is ~100K tokens. The response headers X-CodeRouter-Cost and X-CodeRouter-Savings show per-request counts + what Opus would have cost instead.

How is this different from OpenRouter / LiteLLM?

Those give you one API key for many models — you still pick which model to call. CodeRouter analyzes the phase of your coding request (planning / implementing / debugging / testing / documenting) and routes to the cheapest capable model per call, automatically. OpenRouter solves access; CodeRouter solves cost.

Will Opus still be used for hard problems?

Yes. When the phase detector identifies a planning or complex debug step, the router upgrades to Opus 4.7 or GPT-5.2 — that's why Opus quota exists. For the 80% of your calls that are incremental implementation, test writing, or doc updates, we route to Sonnet 4.6 / DeepSeek V3 / Haiku, where quality is equal and cost is 10–100x lower.

Does CodeRouter work with Cursor / Aider / Claude Code / Copilot?

Any OpenAI-compatible agent. Set your agent's base_url to https://www.coderouter.io/api/v1 and use your CodeRouter API key. Aider and Cursor (custom model) work out of the box. Claude Code via proxy config. See the setup guide.

What happens if I hit the overage cap?

Soft stop — we route your remaining calls to cheaper models and never block service. You get an email alert + dashboard warning. Raise your cap in settings any time (no new contract, no phone call).

Can I cancel anytime?

Yes. Cancel from the dashboard or via Stripe portal. Your plan stays active through the end of your billing period. No retention gates, no salespeople.

Is my code stored?

No prompt content is persisted. We log only routing metadata — model used, token counts, phase classification, latency. The first 500 chars of each prompt are stored temporarily for classifier quality improvement, which you can opt out of in settings.

Do you offer annual pricing?

Yes, annual plans get 2 months free (e.g. Pro annual = $990/yr ≈ $82.50/mo). Toggle the billing period on checkout.