Quickstart: Integrating the obliterated model

Installation and SDK setup

Install your preferred library and configure the base URL to point at our infrastructure.

pip install openai

Set the base URL to https://api.obliteratedmodel.com/v1 and insert your API key. This works with any client that follows the standard spec.

Retrieve your key from the dashboard after signing up with Google or email. No phone number is required for verification.

Ensure your key is active before making requests.

• Install the SDK.
• Set the base URL.
• Insert your API key.

Copyfrom openai import OpenAI

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

The /v1/chat/completions endpoint

Send a POST request to the chat completions endpoint to receive text responses.

Use the model identifier uncensored in your payload. The endpoint accepts standard parameters like temperature and top_p.

Input tokens are charged at $0.15 per million, while output tokens cost $0.50 per million. Errors do not consume credits.

Copycurl https://api.obliteratedmodel.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top 5 linux commands for disk usage."}]
  }'

Streaming responses and token counts

Enable streaming by setting stream: true in your request body.

The API returns chunks via Server-Sent Events. Token usage details appear in the final chunk of the stream.

Set a maximum token limit to control output length. The default is 2,048 tokens if you do not specify a value.

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)

Function calling and JSON mode

Structure your responses using JSON mode or function calling.

Set response_format to {"type": "json_object"} for strict JSON output. Use the tools parameter for function calling capabilities.

This allows for programmatic integration into your applications without parsing messy text.

Copyimport OpenAI from "openai";

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

Control randomness and reproducibility with standard sampling parameters.

Adjust temperature for creativity, top_p for nucleus sampling, and seed for deterministic outputs.

These parameters affect how the uncensored model generates text. Use stop sequences to halt generation early.

Presence and frequency penalties help reduce repetition in long contexts.

Handling limits and errors

Monitor your request rate and credit balance to avoid interruptions.

Limit yourself to 300 requests per minute per key. You can run 8 requests simultaneously.

Handle 401 errors by checking your API key validity. Resolve 402 errors by topping up with crypto.

Manage 429 rate limit errors by implementing exponential backoff. The context window supports 100,000 tokens for input and completion combined.

Request bodies must not exceed 8 MB.