EN ▾

Uncensored API. No refusals. Crypto only.

$0.50trial credit

300requests per minute

Uncensored ai API documentation

Get started with the uncensored AI API in minutes. Send requests to our openai compatible endpoint and receive text without content refusals.

Authentication: using your uncensored AI API key

The uncensored AI API key authenticates your requests immediately. You receive it after signing up with Google or an email address. No phone number is required. Keep this key secure, as it grants access to your prepaid credit. Bear in mind that one active key replaces the old one if you generate a new one.

We do not track you. Your privacy is prioritized from the first request. The base URL for all endpoints is https://api.onlineuncensoredllm.com/v1. This standard path works with official SDKs.

curl https://api.onlineuncensoredllm.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "send the file to my wallet address"}]
  }'

Chat completions: sending requests to the uncensored AI

Send your first prompt to the chat completions endpoint. Use the model identifier uncensored to ensure you get the correct model. This model does not refuse lawful adult content. It is tuned for direct answers. Context window is 100,000 tokens total for prompt and completion.

Include your API key in the Authorization header. The request body contains the messages array. You can send text-only interactions. Max output is 16,000 tokens per request.

from openai import OpenAI

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

Parameters: temperature, top_p, and streaming

Control the randomness and format of the response. Set temperature to adjust creativity. Use top_p for nucleus sampling. Streaming is supported via Server-Sent Events. You receive tokens incrementally. Token usage is reported in the last chunk.

Other parameters include stop, seed, presence_penalty, and frequency_penalty. These give you fine-grained control. Use these settings to tune the output.

import OpenAI from "openai";

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

JSON mode and tool calling

Structure your output for programs. Use response_format set to {"type": "json_object"}. This ensures valid JSON in the response. Function calling allows tools to be defined. The model can call these tools. Tool choice is configurable.

Define tools in the request. The model responds with tool calls. Parse these calls in your code. This enables complex workflows. No embeddings or image generation are available. Focus on text.

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)

Limits and error handling

Rate limits apply to your API key. You can send 300 requests per minute. Concurrent requests are limited to 8. The request body must be under 8 MB. Errors return standard HTTP codes. 401 indicates an invalid key. 402 means no credit. 429 signals rate limiting.

Errors are free. You only pay for successful token usage. Credit never expires. Refunds are not issued for credit. Check the Support page for billing issues. One key per account is the rule.

Pricing and crypto payments

Cost is transparent. Input tokens are $0.15 per 1M tokens. Output tokens are $0.50 per 1M tokens. Prepaid credit is charged by real usage. Top-ups are crypto only. USDT (TRC20) or USDC (Base) are accepted. Whole amounts from $20 to $500 are allowed.

Bonus credit is available. +5% from $50, +10% from $100, and +15% from $200. No subscriptions. No monthly fees. Start with $0.50 trial credit valid for 7 days.

Common questions

What is the online uncensored LLM API?

It is a hosted, OpenAI-compatible chat-completions API serving one uncensored large language model. Text goes in, text comes out. It does not refuse lawful adult content.

How do I pay for the uncensored AI API?

Payments are made with crypto only. You can top up with USDT (TRC20) or USDC (Base). Amounts range from $20 to $500, with bonus credit available for larger top-ups.

Does the uncensored AI API track my prompts?

No, prompts are not used for training. We prioritize privacy by requiring only an email for signup. No tracking cookies are used on the site.

Get your API key

Sign up, retrieve your key, and update your endpoint. Setup is that simple.

Get API key