Is this an openai compatible API for chat completions?

Yes, the endpoint structure matches the standard chat completions format. You can use official OpenAI SDKs by pointing them to our base URL. The model id remains "uncensored" regardless of the client used.

What happens if I get a 402 error?

A 402 error means your prepaid credit balance is zero or insufficient. You must top up using USDT or USDC to resume service. No monthly fees apply, so you only pay when you need to.

How does the uncensored LLM handle context?

The model processes a total of 100,000 tokens for input and output combined. It supports up to 16,000 tokens in a single completion. This allows for deep context analysis without immediate truncation.

API Documentation - OpenAI Compatible Endpoint

Authentication & Base URL

Use your API key for every request to the base URL HTTPS://api.llmwithnorestrictions.com/v1. The system requires this header for authorization and tracks usage against your prepaid credit. You generate a single key during signup, which replaces any previous key immediately. Keep this value secure, as it grants full access to your balance.

curl https://api.llmwithnorestrictions.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of ten Linux commands"}]
  }'

The /v1/chat/completions Endpoint

Send POST requests to /v1/chat/completions to receive text responses. The model identifier is strictly "uncensored" for all interactions. Input text goes into the messages array, and the system returns generated text without content refusals for lawful adult use. You pay only for tokens actually consumed, not for errors.

from openai import OpenAI

client = OpenAI(base_url="https://api.llmwithnorestrictions.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 Responses (SSE)

Enable streaming by setting stream to true in your request. The API returns Server-Sent Events (SSE) for real-time token delivery. This approach reduces perceived latency significantly for large outputs. Token usage details appear in the final chunk of the stream.

stream = 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 & JSON Mode

Support function calling via the tools parameter for structured data extraction. Use response_format with json_object to enforce strict JSON outputs. The model adheres to these schemas reliably, making it suitable for backend automation. You can control tool selection with tool_choice for precise execution.

Token Limits & Context Window

The context window supports up to 100,000 tokens for prompt and completion combined. Maximum output per request is 16,000 tokens, or 2,048 if you omit max_tokens. Requests exceeding the body limit of 8 MB are rejected immediately. Plan your input length to stay within these boundaries.

Error Handling & Rate Limits

Monitor standard HTTP codes for immediate feedback. A 401 status indicates an invalid or expired API key. A 402 error signals insufficient prepaid credit for the requested operation. A 429 response means you have hit the 300 requests per minute limit. Errors and refusals consume no tokens from your balance.

Node.js

import OpenAI from "openai";

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

API Reference & Quickstart