Integrate the uncensored model

Authentication and base URL

Connect using your API key and the dedicated base URL. HTTPS://api.generatoraiunrestricted.com/v1 routes all requests to the single uncensored model. Generate a key via Google or email on the dashboard. The key grants immediate access. No phone number is required. Set the Authorization header to Bearer YOUR_API_KEY. This standard header works with most OpenAI SDKs. You only need one active key per account. Replace older keys by generating a new one. Errors and refusals do not consume credit. Only successful completions are charged. The prepaid system ensures transparent spending. Crypto top-ups support USDT (TRC20) and USDC (Base). Bonuses apply automatically to larger deposits. Check the pricing page for current rates.

Chat completions endpoint

Send prompts to POST /v1/chat/completions. The endpoint accepts standard JSON messages. Define the system role for context. Add user messages for your query. The model responds with generated text. Use the model ID "uncensored" in your requests. This ID points to our dedicated uncensored model. It is not GPT or Claude. The context window supports 100,000 tokens total. Max output is 16,000 tokens per request. Set max_tokens to control length. Omit it for the default 2,048 limit. Streaming is available for real-time feedback. JSON mode enforces strict schema compliance. Function calling enables tool integration. All parameters follow the OpenAI specification.

Copycurl https://api.generatoraiunrestricted.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Check if the system supports concurrent requests."}]
  }'

Python SDK

Use the official OpenAI Python library. Install it via pip. Configure the base URL and API key. Create an instance of the OpenAI client. Pass the custom base URL. The library handles HTTP requests automatically. Send messages using the chat.completions.create method. Specify the model as "uncensored". Access the response text from the object. Iterate through choices if needed. Handle errors gracefully. Check for rate limits or insufficient funds. The SDK supports both synchronous and async modes. Use async for high-throughput applications. Monitor token usage in the response object. This helps track your prepaid credit. Errors are free, so only count successful tokens.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.generatoraiunrestricted.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 SDK

Install the OpenAI Node.js package. Configure the environment variables. Set the base URL to our endpoint. Initialize the client with your API key. Call the chat completions endpoint. Provide the system and user messages. The response contains the generated text. Parse the JSON response if needed. Handle streaming data for live updates. Use the await keyword for async calls. Manage concurrent requests carefully. Respect the 8 concurrent request limit per key. The SDK simplifies header management. It handles retries and timeouts automatically. Check the documentation for advanced options. Use environment variables for secure key storage. This approach works well in serverless environments.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.generatoraiunrestricted.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 responses with SSE

Enable streaming by setting stream: true. The API returns Server-Sent Events. Each chunk contains partial text. Process chunks as they arrive. This reduces perceived latency for users. The final chunk includes token usage data. Calculate costs based on input and output tokens. Errors during streaming still consume no credit. Handle network interruptions gracefully. Reconnect if the stream drops. The SDKs provide helper functions for streaming. Use these for simpler implementation. Monitor the finish_reason for completion. This indicates the end of the generation. Use streaming for long-form content. It provides a better user experience. Display tokens as they generate.

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)

Limits, errors and context window

Respect the 300 requests per minute limit. You can send 8 requests concurrently. The request body must be under 8 MB. A 401 error means your key is invalid. Check your dashboard for the correct key. A 402 error indicates insufficient credit. Top up via crypto to continue. A 429 error signals rate limiting. Wait before retrying. The context window is 100,000 tokens. This includes both prompt and completion. Plan your token usage accordingly. Errors do not charge your credit. Refusals are also free. The model refuses only minor content. Adult content is allowed. Privacy is maintained; prompts are not used for training.