Quickstart: Integrate the uncensored LLM API

Install the official OpenAI SDK

Use the standard library to handle authentication and formatting. This approach ensures compatibility with your existing codebase without learning a new client interface.

• Python: pip install openai
• Node.js: npm install openai

The SDK manages retries and JSON serialization automatically. You do not need to write custom HTTP handlers for basic text generation tasks.

Configure your base URL and API key

Point your client to our specific endpoint to access the unfiltered model. Standard OpenAI URLs will not reach our dedicated uncensored inference engine.

Set the base_url to https://api.aillmwithoutrestrictions.com/v1 and inject your key from the dashboard. The model identifier is always uncensored.

Send your first chat completion request

Make a direct POST request to generate text without content filters. This example uses cURL to demonstrate the raw HTTP interaction.

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

Send a prompt and receive a complete response in one call. The model returns text that bypasses standard corporate guardrails.

Enable streaming for real-time token output

Reduce perceived latency by consuming tokens as they generate. Streaming provides immediate feedback for long-form roleplay or creative writing.

Copyfrom openai import OpenAI

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

Iterate over the stream to display tokens in real-time. The final chunk contains the total token usage for billing.

Use function calling and JSON mode

Structure your output for programmatic use or execute tools dynamically. Both modes are supported within the uncensored environment.

Copyimport OpenAI from "openai";

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

Define tools or force JSON responses using response_format. The model adheres to your schema while maintaining its unrestricted nature.

Handle errors and check usage

Monitor response codes to manage your prepaid credit and rate limits. Errors like 401 indicate an invalid key, while 402 signals empty credit.

The rate limit is 300 requests per minute. Exceeding this triggers a 429 error. Your context window spans 100,000 tokens total, with a max output of 16,000 tokens per request.

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)