Uncensored ai chatgpt API Quickstart

Install your SDK

Start by installing the official client library for your preferred language. The standard OpenAI SDKs work perfectly because we use the same protocol. Install the package using your usual package manager to get ready for configuration.

Configure the base URL

Point your client to our specific endpoint to enable uncensored responses. You must set the base_url to https://api.uncensoredaichatgpt.com/v1 and provide your API key. This small change directs traffic to our servers while keeping your existing integration logic intact.

Copycurl https://api.uncensoredaichatgpt.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of ten unique features for a new streaming platform."}]
  }'

Make your first request

Send a standard chat/completions request using the model ID uncensored. Our model does not refuse lawful adult, fictional, or controversial topics by default. The response returns text directly, allowing you to verify that content filters are inactive in your output.

Copyfrom openai import OpenAI

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

Handle streaming responses

Enable streaming by setting stream: true to receive tokens in real-time. This approach reduces perceived latency for long-form generation or roleplay. Each chunk includes usage data only in the final response, ensuring you can track token consumption accurately without waiting for the full completion.

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)

Use tools and JSON mode

Utilize function calling and strict JSON formatting for structured data extraction. Pass response_format with {"type": "json_object"} to enforce consistent schema output. This capability works alongside standard parameters like temperature and top_p to control creativity while maintaining programmatic reliability.

Monitor token usage

Track your prepaid credit balance through usage metrics returned in the response headers. Errors and refusals do not consume tokens, so you only pay for successful content generation. Your context window supports 100,000 tokens total, with a maximum output limit of 16,000 tokens per request.

Node.js

Copyimport OpenAI from "openai";

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