API Documentation

Base URL and Authentication

Start by pointing your client to https://api.uncensoredaitext.com/v1 and passing your key in the authorization header. This setup works with standard openai compatible clients, allowing you to swap in our service without rewriting your code. You get one active key per account; generating a new one replaces the old immediately. Keep your credentials secure, as they control your prepaid credit.

Copycurl https://api.uncensoredaitext.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize this 500 word article on neural networks."}]
  }'

Chat Completions Endpoint

Send your prompts to POST /v1/chat/completions using the model id uncensored. This endpoint handles text-in, text-out interactions efficiently. You can adjust parameters like temperature and top_p to control creativity. The service supports streaming via Server-Sent Events for real-time token delivery. Errors and refusals do not consume your credit, ensuring fair usage.

Copyfrom openai import OpenAI

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

Models Endpoint

Query GET /v1/models to retrieve available models. This returns a list containing the uncensored model. You can verify connectivity and model availability before sending heavy payloads. The response confirms the API version and available capabilities. Use this to debug connection issues quickly.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uncensoredaitext.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 More

Control output randomness with temperature and top_p. Higher values produce more creative text. Lower values ensure deterministic responses. You can also set stop sequences to halt generation early. The seed parameter helps reproduce results. Adjust presence_penalty and frequency_penalty to reduce repetition. These tools give you precise control over the generation quality.

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)

Streaming Responses via SSE

Enable streaming by setting stream: true in your request. The API sends chunks of tokens as they are generated. This reduces perceived latency for users. Each chunk includes token usage data in the final part. You can handle partial responses gracefully. This is ideal for chat interfaces that update in real-time.

Error Handling and Limits

Monitor your requests for common errors like 401 or 402. A 401 status means your key is invalid. A 402 status indicates insufficient credit. You can top up via crypto at any time. The rate limit is 300 requests per minute. Your context window supports 100,000 tokens total. Keep requests under 8 MB to avoid errors. Handle these cases to maintain a smooth user experience.