Pricing & Billing

Clear Pricing Before You Route Production Traffic

Pricing is more than a model table. Compare model prices, understand pay-as-you-go versus BYOK economics, and see exactly how usage translates into spend.

What to review before you approve budget

Use the model catalog, confirm BYOK fee behavior, and connect usage accounting to your billing workflow before you move meaningful traffic.

Browse model-by-model pricing, context windows, and capabilities before you decide on a routing strategy.

Keep model costs on your own cloud account while understanding when Router AI may still apply a platform fee.

Track every request as auditable cost data with detailed usage breakdowns, activity analytics, and billing reconciliation.

Model CatalogBYOK EconomicsUsage Accounting

Open page Open page Open page

Transparent Pricing

Compare current model pricing for pay-as-you-go and BYOK options.

Claude Sonnet 4.6

Input $3.24 / 1M tokens Output $16.20 / 1M tokens

GPT-4o

Input $2.70 / 1M tokens Output $10.80 / 1M tokens

Gemini 2.5 Pro

Input $1.35 / 1M tokens Output $10.80 / 1M tokens

Anthropic Input $3.24 / 1M tokens Output $16.20 / 1M tokens Openai Input $2.70 / 1M tokens Output $10.80 / 1M tokens Google Input $1.35 / 1M tokens Output $10.80 / 1M tokens

Payments are processed through Stripe Checkout.

Available card and wallet options vary by region and eligibility. The final payment methods are shown in checkout before you confirm the purchase.

SECURE CHECKOUT

Routing plans for every traffic level

Pick the plan that matches how much production traffic you route. Monthly or yearly billing, cancel anytime, usage credited to your account.

Routing plans for every traffic level

Pick the plan that matches how much production traffic you route. Monthly or yearly billing, cancel anytime, usage credited to your account.

Starter

$19

$15 /month, billed yearly

For solo builders putting their first traffic through the router.

Billed yearly. Cancel anytime.

Includes

$180 of routing credit per year
275+ models behind one OpenAI-compatible endpoint
Health-aware routing with automatic failover
Bring your own provider keys (BYOK)
Per-key usage and spend visibility
Email support

Pro

$99

$79 /month, billed yearly

For production apps that need savings evidence and team controls.

Billed yearly. Cancel anytime.

Everything in Starter, plus

$948 of routing credit per year
Approved model basket with shadow-mode savings
Prompt caching on models with a published cached rate
Team seats with per-key budgets and alerts
Request logs with baseline vs selected vs saved
Priority support

Scale

$499

$399 /month, billed yearly

For teams routing meaningful production traffic with governance.

Billed yearly. Cancel anytime.

Everything in Pro, plus

$4,788 of routing credit per year
Region-isolated routing with KMS envelope encryption
Custom routing objectives and fallback policy
Audit trail for every request and configuration change
SSO-ready governance and workspace separation
Dedicated support with a named engineer

Pricing FAQ

Compare model costs, understand BYOK fees, and see how billing works before you scale traffic.

How should a team estimate spend before switching production traffic?

Does BYOK mean Router AI becomes free? Where can I verify what was actually billed? Is the pricing page enough to make a finance decision? It is a good starting point, but not the final source of truth. You should verify your account settings, BYOK fee details, and actual workload mix before treating catalog prices as your total cost estimate.

How should a team estimate spend before switching production traffic?Does BYOK mean Router AI becomes free?Where can I verify what was actually billed?Is the pricing page enough to make a finance decision?

Start building in 3 lines of code

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.routerai.lol/v1",
  apiKey: "sk-your-key",
});

const response = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-4.6",
  messages: [{ role: "user", content: "Hello!" }],
});

OpenAI-Compatible Quickstart

import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.routerai.lol/v1", apiKey: "sk-your-key", }); const response = await client.chat.completions.create({ model: "anthropic/claude-sonnet-4.6", messages: [{ role: "user", content: "Hello!" }], });

Pricing & Billing Clear Pricing Before You Route Production Traffic Pricing is more than a model table. Compare model prices, understand pay-as-you-go versus BYOK economics, and see exactly how usage translates into spend. Browse model catalog Read usage accounting What to review before you approve budget Use the model catalog, confirm BYOK fee behavior, and connect usage accounting to your billing workflow before you move meaningful traffic. Model Catalog Browse model-by-model pricing, context windows, and capabilities before you decide on a routing strategy. Open page BYOK Economics Keep model costs on your own cloud account while understanding when Router AI may still apply a platform fee. Open page Usage Accounting Track every request as auditable cost data with detailed usage breakdowns, activity analytics, and billing reconciliation. Open page Transparent Pricing Compare current model pricing for pay-as-you-go and BYOK options. View all pricing Anthropic Claude Sonnet 4.6 Input $3.24 / 1M tokens Output $16.20 / 1M tokens Openai GPT-4o Input $2.70 / 1M tokens Output $10.80 / 1M tokens Google Gemini 2.5 Pro Input $1.35 / 1M tokens Output $10.80 / 1M tokens SECURE CHECKOUT Payments are processed through Stripe Checkout. Available card and wallet options vary by region and eligibility. The final payment methods are shown in checkout before you confirm the purchase. Pricing FAQ Compare model costs, understand BYOK fees, and see how billing works before you scale traffic. How should a team estimate spend before switching production traffic? Does BYOK mean Router AI becomes free? Where can I verify what was actually billed? Is the pricing page enough to make a finance decision? It is a good starting point, but not the final source of truth. You should verify your account settings, BYOK fee details, and actual workload mix before treating catalog prices as your total cost estimate. Start building in 3 lines of code import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.routerai.lol/v1", apiKey: "sk-your-key", }); const response = await client.chat.completions.create({ model: "anthropic/claude-sonnet-4.6", messages: [{ role: "user", content: "Hello!" }], }); Get API Key OpenAI-Compatible Quickstart

Pricing FAQ

Compare model costs, understand BYOK fees, and see how billing works before you scale traffic.

How should a team estimate spend before switching production traffic?

Start with the model catalog to compare current prompt and completion pricing, then test with your own prompt mix and traffic patterns before changing production routing policy.

Does BYOK mean Router AI becomes free?

No. BYOK keeps model charges on your own cloud account, but Router AI may still charge a platform fee depending on your plan and account settings.

Where can I verify what was actually billed?

Check the response usage object for per-request cost details, then reconcile with activity analytics and the billing dashboard for balances and billing history.

Is the pricing page enough to make a finance decision?

It is a good starting point, but not the final source of truth. You should verify your account settings, BYOK fee details, and actual workload mix before treating catalog prices as your total cost estimate.