Gemini SDK

PulseNeko5/20/26Less than 1 minute

Bridge supports Gemini native protocol (generativelanguage.googleapis.com compatible).

Python

from google import genai

client = genai.Client(
    api_key="sk-your-key",
    http_options={"base_url": "https://bridge.pulseneko.com/gemini"},
)

resp = client.models.generate_content(
    model="gemini-3.1-pro",
    contents="Introduce PulseNeko Bridge in one sentence.",
)
print(resp.text)

Base URL suffix is /gemini

Not /v1. Bridge uses /gemini as the prefix for Gemini-native routing (followed by /v1beta/models/...).

Node.js

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.PULSENEKO_KEY,
  httpOptions: { baseUrl: "https://bridge.pulseneko.com/gemini" },
});

const resp = await ai.models.generateContent({
  model: "gemini-3.1-pro",
  contents: "Hello",
});
console.log(resp.text);

Streaming

for chunk in client.models.generate_content_stream(
    model="gemini-3.1-pro",
    contents="...",
):
    print(chunk.text, end="", flush=True)

OpenAI-compatible fallback

If your codebase is OpenAI-shaped, Gemini models also work via /v1/chat/completions:

from openai import OpenAI

client = OpenAI(
    base_url="https://bridge.pulseneko.com/v1",
    api_key="sk-your-key",
)

resp = client.chat.completions.create(
    model="gemini-3.1-pro",
    messages=[{"role": "user", "content": "Hello"}],
)

Gemini-specific features (Google Search grounding, custom safety settings) don't pass through this path.

Recommended models

Model	Best for
`gemini-3.1-pro`	Daily driver
`gemini-3.1-flash`	Fast / cheap
`gemini-3.0-pro-preview`	Same price as 3.1-pro (legacy)