Temperature & Limits
Learn how to control model randomness and protect your budget with strict generation limits. Setting WithTemperature(0.0) guarantees deterministic outputs, while WithMaxTokens(5) prevents runaway output billing.
Runnable Go Code
examples/temperature_and_sampling/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("Temperature and Minimal Output Caps")
gw, err := gateway.New(
gateway.WithModelList(
gateway.ModelEntry{
ModelName: "sampling-chat",
Model: "openai/gpt-4o-mini",
APIKey: "os.environ/OPENAI_API_KEY",
},
),
gateway.WithDemoMocksIfEnvMissing(),
gateway.WithSilentLogs(),
)
if err != nil {
demoutil.Fail("Gateway initialization failed", err)
}
defer gw.Close()
// Strict determinism: Temperature 0.0, MaxTokens capped to 5
res, err := gw.Chat(ctx, "sampling-chat", "Pick a single letter.",
gateway.WithTemperature(0.0),
gateway.WithMaxTokens(5),
)
if err != nil {
demoutil.Fail("Request failed", err)
}
demoutil.Info("Temperature", "0.0 (Deterministic)")
demoutil.Info("Max Tokens Cap", "5")
demoutil.Info("Tokens Consumed", fmt.Sprintf("%d", res.Usage.CompletionTokens))
demoutil.Success("Deterministic Output", res.Content)
demoutil.Done()
}