Documentation for developers

Authentication & Base URL

Start every request with your API key and the provided base URL. Our API uses standard bearer token authentication. You receive a single key immediately after signup. Use https://api.obliteratedllm.com/v1 as your base URL. No complex routing or vendor selection is needed. Just paste your key and go.

First Request

Send a simple chat completion to test connectivity. Use the uncensored model ID. The API returns text directly without extra processing. You can adjust parameters like temperature later. Start with a basic system message to set the tone.

Copycurl https://api.obliteratedllm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "return json with keys name and age"}]
  }'

Python SDK Integration

Use the official OpenAI Python library for easy integration. Set the base URL and API key in your client configuration. This approach works with existing codebases that expect OpenAI endpoints. You get full access to parameters like top_p and seed.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.obliteratedllm.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 Setup

Integrate with JavaScript or TypeScript projects using the Node SDK. Configure the base URL to point to our hosted endpoint. This allows you to maintain compatibility with standard OpenAI patterns. You can handle errors and responses just like any other API client.

Copyimport OpenAI from "openai";

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

Receive tokens in real-time using Server-Sent Events. This reduces perceived latency for interactive applications. The last chunk includes the final token usage statistics. Streaming is enabled by setting stream: true in your request. Handle partial responses gracefully in your UI.

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)

Limits, Errors & Context

Manage rate limits and understand error codes. You get 300 requests per minute per key. Requests are limited to 8 simultaneous per key. The context window supports 100,000 tokens total. A 401 error means your key is invalid. A 402 error indicates insufficient prepaid credit. A 429 error signals you hit the rate limit. Errors and refusals do not consume credit. Max output is 16,000 tokens unless you specify otherwise.