Gemini (Native Mode) | Enterprise Router

Setup

Install the Google Generative AI SDK:

$ pip install google-generativeai

Configure the client to use your gateway:

1 import google.generativeai as genai
2 
3 genai.configure(
4     api_key="sk-proxy-YOUR_KEY_HERE",
5     transport="rest",
6     client_options={"api_endpoint": "https://gateway.example.com/gemini"}
7 )

Basic generation

1 model = genai.GenerativeModel("gemini-2.5-flash")
2 
3 response = model.generate_content("Explain quantum computing in one paragraph.")
4 
5 print(response.text)

Streaming

1 model = genai.GenerativeModel("gemini-2.5-flash")
2 
3 response = model.generate_content(
4     "Write a haiku about APIs.",
5     stream=True
6 )
7 
8 for chunk in response:
9     print(chunk.text, end="")

Multi-turn conversation

1 model = genai.GenerativeModel("gemini-2.5-flash")
2 chat = model.start_chat()
3 
4 response = chat.send_message("What's the capital of France?")
5 print(response.text)
6 
7 response = chat.send_message("What's its population?")
8 print(response.text)

Using REST directly

If you prefer raw HTTP, Gemini’s REST API works through the gateway. The model name goes in the URL path:

$ curl -X POST "https://gateway.example.com/gemini/v1beta/models/gemini-2.5-flash:generateContent" \
>   -H "x-goog-api-key: sk-proxy-YOUR_KEY_HERE" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "contents": [
>       {"parts": [{"text": "Hello, how are you?"}]}
>     ]
>   }'

For streaming, use the streamGenerateContent method with alt=sse:

$ curl -X POST "https://gateway.example.com/gemini/v1beta/models/gemini-2.5-flash:streamGenerateContent?alt=sse" \
>   -H "x-goog-api-key: sk-proxy-YOUR_KEY_HERE" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "contents": [
>       {"parts": [{"text": "Write a short story."}]}
>     ]
>   }'

Notes

Model in URL path: Unlike OpenAI and Anthropic, Gemini identifies the model in the URL path (/models/{model}:generateContent), not in the request body.
Auth header: The gateway uses the x-goog-api-key header for Gemini authentication.

Supported models

gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-flash-lite
gemini-3.1-pro-preview, gemini-3-flash-preview

New Gemini models work automatically.