Skip to main content
Google AI Studio provides Gemini models. Google requires you to bring your own key—ngrok-managed keys are not available for Google.

​
Setup

1

Create an AI Gateway endpoint

If you don’t have one yet, follow the quickstart to create your AI Gateway endpoint.
2

Get a Google AI API key

Generate an API key at aistudio.google.com. Keys are available on the free tier.
3

Make a request

Pass your key directly—the gateway forwards it to Google.
from openai import OpenAI

client = OpenAI(
    base_url="https://your-ai-gateway.ngrok.app/v1",
    api_key="AIza..."  # Your Google AI key, forwarded by gateway
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

​
Available models

See the model catalog for the full list of supported Gemini models.

​
Store key in the gateway

Instead of each client passing their own key, you can store it once in ngrok Secrets and have the gateway inject it automatically.
Storing your provider key in the gateway makes your endpoint publicly accessible. You must add authorization to prevent unauthorized use and unexpected charges. See Protecting BYOK Endpoints.
1

Store your key in ngrok secrets

ngrok api secrets create \
  --name google \
  --secret-data '{"api-key": "AIza..."}'
Or use the Vaults & Secrets dashboard.
2

Configure your traffic policy

on_http_request:
  - type: ai-gateway
    config:
      providers:
        - id: "google"
          api_keys:
            - value: ${secrets.get('google', 'api-key')}
3

Make a request

Clients no longer need a Google key—pass any value for api_key.
from openai import OpenAI

client = OpenAI(
    base_url="https://your-ai-gateway.ngrok.app/v1",
    api_key="unused"  # Gateway injects your Google key
)

response = client.chat.completions.create(
    model="gemini-2.5-flash",
    messages=[{"role": "user", "content": "Hello!"}]
)

print(response.choices[0].message.content)

​
Next steps