API Documentation

Quickstart: Your First Request

The uncensored LLM API uses the standard POST /v1/chat/completions endpoint. Point your client to the base URL and include your key. The model identifier is uncensored. This works with any OpenAI-compatible SDK.

Send a simple message to verify connectivity. The service returns text directly. Errors like 401 indicate an invalid key. Use the provided code to test your setup.

Authentication and API Keys

API keys are issued immediately upon signup via Google or email. Pass the key in the Authorization: Bearer <key> header. One active key exists per account; generating a new key replaces the old one. The limit is 300 requests per minute.

Endpoints: /v1/chat/completions and /v1/models

Use GET /v1/models to verify availability. Send text to POST /v1/chat/completions. The base URL is https://api.abliteratedaionline.com/v1. No embeddings or image endpoints exist. Requests are text in, text out.

Parameters: Temperature, Top P, and More

Control creativity with temperature and top_p. Set stop sequences for clean cuts. Use seed for reproducibility. JSON mode requires response_format set to json_object. Adjust penalties for frequency and presence.

Streaming Responses with SSE

Enable streaming by setting stream to true. Tokens arrive via Server-Sent Events. Token usage details appear in the final chunk. This method reduces perceived latency for long outputs.

Error Handling and Rate Limits

Handle 401 for bad keys and 402 for insufficient credit. 429 indicates rate limits. The context window is 100,000 tokens. Max output is 16,000 tokens. Errors and refusals consume no credit.

Model Capabilities: Context Window and Max Tokens

The model supports a 100,000 token context window. This includes both the prompt and the completion. The maximum output per request is 16,000 tokens. Default max tokens is 2,048. This allows for extensive conversation history.

cURL

Copycurl https://api.abliteratedaionline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "fix the syntax error in this python loop"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.abliteratedaionline.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.js

Copyimport OpenAI from "openai";

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

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)