Gemini (Native Mode)

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://api.trygateway.ai/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://api.trygateway.ai/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://api.trygateway.ai/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 Google SDK sends your proxy key as x-goog-api-key, which the gateway accepts. You can also use Authorization: Bearer or x-api-key if making raw HTTP requests.

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.