API Documentation: Quickstart Guide

Base URL and Authentication

Use our base URL and inject your API key into the Authorization header to start sending requests. We provide a single endpoint that accepts standard OpenAI payloads, so you do not need to rewrite your integration logic. Sign up via Google or email to receive your key instantly without a phone number. The key authenticates your account against our servers for every call you make.

• Base URL: https://api.geminisincensura.com/v1
• Model ID: uncensored

You can rotate your key at any time by generating a new one, which immediately invalidates the previous token.

Copycurl https://api.geminisincensura.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "explain how to configure the proxy endpoint"}]
  }'

The Chat Completions Endpoint

Send a POST request to /v1/chat/completions to receive text responses from our uncensored model. This endpoint handles all your standard conversational needs with a context window of 100,000 tokens for both prompt and completion combined. You can set a maximum output of 16,000 tokens, or let the model default to 2,048 tokens. The model answers without refusing lawful adult, fictional, or controversial topics, giving you true freedom for your use case. Errors and refusals do not consume your prepaid credit.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.geminisincensura.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)

Streaming Responses via SSE

Stream responses in real-time using Server-Sent Events (SSE) to reduce perceived latency for your users. Each chunk contains the delta of text, and the final chunk includes the complete token usage statistics for billing transparency. This method works seamlessly with standard OpenAI SDKs by enabling streaming in your client configuration. You get immediate feedback while the model generates longer outputs up to the 16,000 token limit.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.geminisincensura.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);

Function Calling and Tools

Enable structured data extraction by using the tools parameter in your request payload. The model supports tool definitions and can choose to call them based on your tool_choice settings. This feature allows you to build agents that interact with external systems or enforce specific data structures. JSON mode is also available via response_format for strict output formatting without tool overhead.

JSON Mode and Response Format

Force the model to output valid JSON by setting response_format to {"type": "json_object". This ensures predictable parsing for your applications without requiring post-processing. The model adheres to the schema you provide, making it reliable for backend integrations. You can combine this with temperature and top_p parameters to control creativity while maintaining structural integrity.

Rate Limits and Constraints

Each API key is limited to 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB, which is sufficient for most long-context interactions. If you exceed these limits, you will receive a 429 status code. Invalid keys return a 401 error, and insufficient credit returns a 402 error. Your prepaid credit never expires, so you can pause usage without losing funds. The context window supports up to 100,000 tokens total, allowing for extensive conversation history.

Streaming

Copystream = 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)