Uncensored API

LLM proxy for uncensored generation

A cheap LLM proxy that serves one uncensored model via the standard OpenAI-compatible endpoint, allowing you to swap your base URL and key in seconds for unrestricted text generation at scale.

$0.15 per 1M input tokens
100k token context window
Crypto payments only

Create key View documentation

https://api.proxyllm.cc/v1uncensored

curl https://api.proxyllm.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List five common CSS layout techniques for modern web design."}]
  }'

from openai import OpenAI

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

import OpenAI from "openai";

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

per 1M input tokens: $0.15
Output tokens / 1M: $0.50
token context: 100,000
trial credit: $0.50
requests per minute: 300

Core capabilities

Drop-in compatibility

Use the official SDKs by simply changing the base URL and API key in your existing configuration.

Single uncensored model

We serve one open-weight model tuned to answer without content refusals for lawful adult use cases.

Transparent per-token pricing

Pay only for real usage with prepaid credit that never expires and errors are charged at zero.

Crypto top-ups

Fund your account with USDT (TRC20) or USDC (Base) for amounts between $20 and $500.

Privacy first

Prompts are not used for training and account creation requires only an email address or Google login.

Developer features

Supports streaming via SSE, JSON mode, function calling, and standard parameters like temperature and top_p.

Setup guide

1
Get your key
Sign up with Google or email to receive your API key immediately without phone verification.
2
Add crypto credit
Deposit USDT or USDC to fund your account and start sending requests to the endpoint.
3
Update base URL
Point your existing code to our endpoint and begin generating unrestricted text with zero code changes.

Community projects

AI coding agents

Connect tools like Claude Code to a proxy that handles requests without content filters blocking output.

Chatbot backends

Build unfiltered chat interfaces that respond to controversial or adult topics without triggering standard provider refusals.

Content generation

Generate creative text for fictional stories or research where standard models might censor specific themes.

Cost control

Prevent runaway costs by using prepaid credit with no monthly subscriptions and no hidden fees.

Who uses it, in which real situations; and plainly who it is NOT for

Developers needing unrestricted text generation use this LLM proxy for creative writing, security research, and adult content without provider refusals. It suits scripts requiring direct base_url swaps. However, it is NOT for teams needing embeddings, image, or audio generation. Nor does it serve projects requiring model routing or SLA guarantees. It is a single model endpoint for uncensored text only.

Drop-in LLM proxy: use cases for uncensored text

This LLM proxy routes requests to a single uncensored model via standard endpoints, keeping your code unchanged while removing content refusals.

Direct code integration

Change the base URL and API key in your client configuration. The endpoint accepts POST requests to /v1/chat/completions with standard JSON payloads.

Streaming responses

Enable Server-Sent Events to receive tokens in real-time. Your application processes each chunk as it arrives, reducing perceived latency significantly.

Unfiltered creative writing

Generate long-form content without sudden topic restrictions. The model handles mature themes and controversial angles without defaulting to generic refusals.

What developers actually ask about this topic

Use our uncensored LLM proxy by swapping the base URL and key. We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors incur zero cost, and prepaid credit never expires. Sign up via Google or email to receive $0.50 trial credit immediately. Top up exclusively with USDT or USDC to access unlimited generation without monthly subscriptions or hidden fees.

Worked cost examples with token arithmetic

Costs scale linearly with token volume. Input charges $0.15 per million tokens; output runs $0.50 per million. A 10k input plus 2k output request costs roughly $0.002. Errors incur zero charges. You pay only for actual usage, avoiding subscription lock-ins. Crypto tops start at $20. Balance never expires. Track usage via the dashboard to prevent runaway bills.

How this differs from a typical alternative

Our uncensored LLM charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no subscription lock-ins or hidden monthly fees. You pay only for real token usage. Errors and refusals are free. This keeps costs predictable without complex billing.

A checklist for choosing a provider in this niche

Verify token pricing and payment methods immediately. Ensure the base_url supports drop-in OpenAI compatibility. Confirm context limits, such as our 100k window. Check if streaming and JSON mode are available. Avoid providers demanding monthly subscriptions for uncensored access.

Common questions

What is an LLM proxy and how does ProxyLLM work?

It is a middleware routing requests to our uncensored model. You change the base_url and key in your code. This keeps your upstream secrets safe while enabling unrestricted text generation without vendor lock-ins or complex routing logic.

Does this API support function calling and streaming responses?

Yes. We support streaming via Server-Sent Events and function calling with tools. You can also enforce JSON mode for structured outputs. Every token counts toward your prepaid balance, and errors during generation do not consume credit.

How much does the uncensored model cost per token?

Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. You pay only for real usage. Errors are free, and prepaid credit never expires. There are no monthly subscription fees or hidden charges.

Can I pay with cryptocurrency for this cheap LLM API?

Yes. We accept USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500. You receive bonus credit for larger amounts.

What is the context window and maximum output length?

The context window is 100,000 tokens for prompt and completion combined. You can request up to 16,000 output tokens per request. If you do not set max_tokens, the default limit is 2,048 tokens for each completion turn.

Do you use user prompts for training the model?

No. Your prompts are not used for training. We prioritize privacy for developers who need reliable, unrestricted endpoints. You can use the model for lawful adult content, security research, or fiction without worrying about data retention policies.

Your API key is one form away

Create key