API Documentation

Quickstart with the Official SDK

Start generating text immediately using your preferred language client. The API mirrors the standard chat completions interface, so you only need to swap the base URL and API key. This ensures your existing infrastructure works without rewriting logic.

Copycurl https://api.abliteratedmeaning.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the definition of abliterated."}]
  }'

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

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

Base URL and Authentication

Direct all requests to the dedicated base URL with your unique API key in the authorization header. This key is the only credential needed for every request to the /v1/chat/completions endpoint.

Copycurl https://api.abliteratedmeaning.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Return the definition of abliterated."}]
  }'

Chat Completions Endpoint

Send text data to receive raw text output from the uncensored model. Use the uncensored model ID to access the tuned version that skips typical corporate guardrails. The endpoint supports standard JSON payloads, including temperature, top_p, and stop sequences for precise control over the generation process.

Copyfrom openai import OpenAI

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

Streaming and Tool Usage

Enable real-time token delivery by setting the stream parameter to true in your request body. This returns Server-Sent Events (SSE) where the final chunk contains the total token usage for billing transparency. You can also define tools for function calling or force JSON output using the response_format parameter.

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)

Parameters and Limits

Control the model behavior with standard parameters like temperature and seed, but respect the hard limits of the system. Each request can contain up to 100,000 tokens for the context window, with a maximum output of 16,000 tokens per call. If you do not specify max_tokens, the default output is capped at 2,048 tokens.