GeminiaAPI 快速入門指南

API 快速入門指南

使用標準 OpenAI 相容端點將您的客戶端連接到我們的無審查 LLM API，並使用生成的 API 金鑰進行身份驗證。

基礎 URL 與驗證

所有請求的基礎 URL 為 https://api.geminiaiuncensored.com/v1。將您的金鑰傳入 Authorization header 作為 bearer token。此設定適用於任何接受自訂基礎 URL 的 SDK。

發送您的第一個請求

向以下網址發送 POST 請求 /v1/chat/completions 使用模型 ID uncensored。API 會回傳未經內容過濾的原始文字，適用於合法的成人主題。

設定 model 以 uncensored.
包含您的 messages
Use standard parameters like temperature.

This confirms your key works and returns immediate text output.


Python SDK Integration
Initialize the client with your base URL and key. Send a simple prompt to test the connection. The response object contains the generated text in choices[0].message.content.
Node SDK Integration
Configure the client with the same base URL. Use the chat.completions.create method. The response structure mirrors the standard OpenAI format.
Streaming Responses with SSE
Enable streaming by setting stream: true. The API sends Server-Sent Events for each token. Handle the content field in each chunk to build the final response incrementally.
Limits and Errors
Expect a 401 if the key is invalid. A 402 means you need to top up with crypto. Rate limits are 300 requests per minute. The context window is 100,000 tokens. Handle refusals for minor sexual content.
cURL
curl https://api.geminiaiuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a Python function to calculate factorial recursively"}]
  }'
Python
from openai import OpenAI

client = OpenAI(base_url="https://api.geminiaiuncensored.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)
Node.js
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.geminiaiuncensored.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);
Streaming
stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

`Frequently asked questions`

№ 0273-02

Is this the official Gemini API?

No, we run our own uncensored model. It is compatible but not affiliated with Google.

How do I pay?

We accept USDT on TRC20 or USDC on Base. Credits never expire.

What is the context window?

The model supports 100,000 tokens for input and output combined.

`Obtain your API key`

Register, retrieve your key, update your base URL. That covers the entire setup.

Create key