Rate Limiting
Learn how to configure sliding-window token bucket rate limits (RPM: 2) to protect upstream quotas and enforce tenant fairness.
Runnable Go Code
examples/sliding_window_rate_limiting/main.go
package main
import (
"context"
"fmt"
"github.com/goroute-ai/ai-gateway-go-docs/examples/demoutil"
"github.com/goroute-ai/ai-gateway-go/pkg/gateway"
)
func main() {
ctx := context.Background()
demoutil.Banner("Sliding-Window Rate Limiting (RPM/TPM Quotas)")
// Configure strict RPM (Requests Per Minute) cap
gw, err := gateway.New(
gateway.WithModelList(
gateway.ModelEntry{
ModelName: "rate-limited-model",
Model: "gemini/gemini-2.5-flash-lite",
RPM: 2, // Limit to 2 requests per minute
},
),
gateway.WithDemoMocksIfEnvMissing(),
gateway.WithSilentLogs(),
)
if err != nil {
demoutil.Fail("Gateway initialization failed", err)
}
defer gw.Close()
demoutil.Info("Configured Quota", "2 RPM sliding window")
for i := 1; i <= 3; i++ {
res, err := gw.Chat(ctx, "rate-limited-model", "ping", gateway.WithMaxTokens(1))
if err != nil {
demoutil.Info(fmt.Sprintf("Request #%d", i), fmt.Sprintf("QUOTA EXCEEDED: %v", err))
} else {
demoutil.Info(fmt.Sprintf("Request #%d", i), fmt.Sprintf("ALLOWED: %s (Tokens: %d)", res.Model, res.Usage.TotalTokens))
}
}
demoutil.Success("Rate Limiter Status", "Sliding window token bucket strictly enforced")
demoutil.Done()
}