Quickstart: Connect Your SDK
Replace your current endpoint with our base URL and inject your API key into the header. This simple swap routes your requests to the uncensored model immediately.
The base URL is https://api.geminisenzacensura.com/v1. Authentication relies on a Bearer token passed in the Authorization header. You generate this key instantly after signing up with Google or email.
- No extra libraries required.
- Works with any OpenAI-compatible client.
- Immediate availability upon key creation.
This approach eliminates proxy wrappers and complex local setups.
curl https://api.geminisenzacensura.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "What is the capital of Peru?"}]
}'Endpoint: POST /v1/chat/completions
Send your prompt to the chat completions endpoint to receive text output. This single endpoint handles all inference for the uncensored model.
Specify the model ID as "uncensored" in your request body. The API returns standard JSON responses containing the generated text. You can control behavior using parameters like temperature or top_p.
Input goes in, text comes out. No embeddings or image generation here.
from openai import OpenAI
client = OpenAI(base_url="https://api.geminisenzacensura.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)Endpoint: GET /v1/models
Query this endpoint to verify connectivity and list available models. It returns a JSON object containing the model details.
Use this to confirm your API key has valid permissions before sending heavy payloads. The response confirms the model ID "uncensored" is active.
This is a lightweight check that consumes minimal tokens.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.geminisenzacensura.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);Parameters: Temperature, Top-p, and Tools
Control randomness and structure using standard OpenAI parameters. Set temperature for creative variance or top_p for nucleus sampling.
Enable function calling by passing a tools array. The model supports JSON mode via response_format: {"type": "json_object"}. You can also set stop sequences and a seed for reproducibility.
These parameters give you precise control over the uncensored AI output without needing custom logic.
Streaming Responses & Token Usage
Enable streaming by setting stream: true to receive chunks via Server-Sent Events (SSE). This reduces perceived latency for long responses.
The final chunk in the stream contains the total token usage for the request. This allows you to track costs in real-time without waiting for the full response.
Streaming is ideal for chat interfaces or progressive text rendering.
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)Error Codes & Limits
Handle errors gracefully by checking the HTTP status code. A 401 indicates an invalid or expired API key. A 402 means you have insufficient prepaid credit. A 429 signals that you have hit the rate limit.
The limit is 300 requests per minute per key. The request body size is capped at 8 MB. Errors and refusals do not consume your prepaid credit, ensuring you only pay for actual token usage.
Check the response body for a detailed error message to troubleshoot quickly.
