API Documentation

Base URL and Authentication

Start by pointing your client to our base URL and passing your key in the authorization header. We provide a single endpoint that accepts standard OpenAI payloads without requiring custom headers or complex routing logic. Your API key grants access to the dedicated uncensored model, and you can generate one instantly via the dashboard using Google or email authentication. Keep your key secure, as it is the only credential needed for all requests.

Copycurl https://api.howtouseuncensoredai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the current temperature in london"}]
  }'

Chat Completions Endpoint

Send your prompts to the chat/completions endpoint using the standard messages array structure. You must specify the model ID as uncensored to ensure you are hitting the correct inference engine. The API returns text responses that respect your temperature and top-p settings without hidden refusals for lawful content. This simple structure allows you to drop our service into existing projects with minimal code changes.

Streaming and Token Usage

Enable streaming by setting stream: true to receive tokens as they are generated via Server-Sent Events. This reduces perceived latency for long responses and allows your interface to update in real time. Token usage details are included in the final chunk of the stream, so you can track costs accurately without storing the entire response in memory. Errors during streaming do not incur charges for the partial output.

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)

Function Calling and JSON Mode

Use the tools parameter to enable function calling, allowing the model to output structured data for your applications. You can also force JSON output by setting response_format to {"type": "json_object"} for strict schema compliance. These features work alongside our uncensored model, so you get structured outputs without losing the model's ability to handle complex or niche topics. Define your function schemas clearly to get reliable results.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.howtouseuncensoredai.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 Integration

Integrate quickly using the official OpenAI Node SDK by overriding the base URL to point to our service. This ensures compatibility with existing wrappers and middleware that expect standard OpenAI behavior. You can handle errors gracefully and manage retries based on the status codes returned by our API. The SDK handles serialization and deserialization, letting you focus on your application logic rather than HTTP details.

Copyimport OpenAI from "openai";

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

Rate Limits and Quotas

Our API enforces a limit of 300 requests per minute per key, with a concurrency cap of 8 simultaneous requests. If you exceed these limits, you will receive a 429 error, and invalid keys return a 401 error. A 402 error indicates insufficient prepaid credit, which you can top up using USDT or USDC. The model supports a context window of 100,000 tokens, allowing for extensive input data while maintaining performance.