Developer Quickstart: Uncensored API

Base URL and Authentication

Start by setting your base_url to https://api.abliteratedmodels.cc/v1. Authenticate every request by including your API key in the Authorization header as a Bearer token. You can generate a key immediately after signing up via Google or email on the Get API key page. The key is displayed once; store it securely in your environment variables.

• Header: Authorization: Bearer YOUR_API_KEY
• No additional query parameters are required for auth.

Ensure your client library supports custom base URLs. This allows you to swap out the default OpenAI endpoint without changing your code structure.

First Request

Send a POST request to /v1/chat/completions with the model ID uncensored. The API accepts standard chat completion parameters. Text goes in, text comes out. There are no embeddings or image generation endpoints.

• Model: uncensored
• Endpoint: POST /v1/chat/completions

Use the following curl command to verify connectivity:

Copycurl https://api.abliteratedmodels.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Python SDK Integration

The official OpenAI Python SDK works directly with this API. Initialize the client with the correct base URL and your key. This approach abstracts the HTTP details while maintaining full control over parameters like temperature and top_p.

• Use OpenAI(base_url=..., api_key=...)
• Call client.chat.completions.create()

Here is a minimal example for a coding llm task:

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.abliteratedmodels.cc/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

For Node.js environments, use the openai npm package. Configure the baseURL to point to our server. This method is ideal for backend services or serverless functions where you need programmatic access to the uncensored model.

• Install the openai package
• Set baseURL to https://api.abliteratedmodels.cc/v1

Example implementation:

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.abliteratedmodels.cc/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 Responses (SSE)

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE). Token usage statistics are included in the final chunk. This reduces perceived latency for end-users during content generation.

• Set stream: true
• Parse SSE events on the client or server

Code snippet for 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)

Rate Limits and Context Window

Each API key allows 300 requests per minute and 8 concurrent requests. The request body must not exceed 8 MB. The context window is 100,000 tokens total. There is no separate output cap; if max_tokens is unset, the response can run to the end of the window. If you hit the limit, your requests will queue or fail. Manage concurrency to stay within the 8 concurrent request threshold. Check the Pricing page for credit details.