EN ▾

Uncensored Text API

cheap LLM API for uncensored text generation

  • $0.15per 1M input tokens

A single, highly optimized uncensored model available via a standard OpenAI-compatible interface. No monthly fees, no model routing, just raw text generation at $0.15 per 1M input tokens.

Get API keyRead the docs

  • $0.15 per 1M input tokens
  • No minimum spend required
  • $0.50 free trial credit

Try it in one request

curl https://api.cheapllmapis.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'
  • $0.50Output tokens / 1M
  • 100,000token context
  • $0.50trial credit
  • 300requests per minute

What you get

  1. OpenAI-Compatible Interface

    Use the official OpenAI SDKs or any compatible client by simply changing the base_url. Supports streaming via SSE and tool/function calling out of the box.

  2. Single Uncensored Model

    We run one open-weight model tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or any other vendor's model.

  3. 100k Context Window

    Process large documents with a combined prompt and completion window of 100,000 tokens. Ideal for long-context tasks without complex chunking strategies.

  4. Transparent Pay-As-You-Go

    Prepaid credit with no expiration. Top-ups start at $20, with bonus credits available for larger deposits. No hidden subscription fees or tier locks.

  5. Developer Simplicity

    No card required for the trial. Generate your API key instantly with just an email and password. Regenerate keys anytime to revoke access.

  6. Privacy Focused

    Your prompts are not used for training. We keep account setup minimal with no phone number required, respecting your data while you build.

How it works

  1. Create Account

    Sign up with an email and password to receive your unique API key instantly.

  2. Configure SDK

    Set your base_url to https://api.cheapllmapis.com/v1 and inject your API key into your client.

  3. Send Requests

    Make POST requests to /v1/chat/completions with model id 'uncensored' and start generating text.

What people build with it

  1. Content Generation

    Produce creative stories, marketing copy, or dialogue without hitting standard refusal filters. Ideal for writers who need raw output without editing around safety gates.

  2. AI Roleplay

    Run character-driven bots that maintain personality and respond to adult or controversial topics naturally. Perfect for interactive fiction platforms.

  3. Data Annotation

    Generate labeled data or summaries for training datasets without bias from corporate content policies. Useful for research and development teams.

  4. Code Assistance

    Get uncensored technical explanations and code snippets without unnecessary verbosity. Great for developers who want direct answers to complex queries.

Why Choose Our Uncensored LLM API?

Most LLM APIs aggregate dozens of models behind a relay, often adding latency and complexity. We offer a single, highly optimized uncensored model that answers without content refusals for lawful adult use. This means you get consistent behavior and predictable costs without the overhead of model routing. Our model is an open-weight solution run on our own GPU servers, ensuring you aren't just reselling someone else's infrastructure. It is not GPT, Claude, Gemini, or any other vendor's model. We prioritize developer simplicity: you interact with a standard interface that feels familiar if you have used OpenAI before. The model is tuned to handle controversial, security-research, or fictional topics without unnecessary hedging. This approach gives you direct access to raw text generation capabilities. You avoid the premium pricing of enterprise-grade models while still getting high-quality output. If you need raw text without corporate safety filters, this is the most direct path to that goal.

Developer-First: Standard OpenAI SDK Compatibility

Integration takes seconds because we follow the standard OpenAI chat-completions structure. You can use the official OpenAI SDKs or any client that supports the OpenAI protocol. Simply update your base_url to https://api.cheapllmapis.com/v1 and provide your API key. The model id to send is "uncensored". We support streaming via Server-Sent Events (SSE) for real-time token output, which is essential for chat interfaces. Tool and function calling are also supported, allowing you to integrate this API into more complex agent workflows. There are no embeddings, image, audio, or video generation capabilities—just text in and text out. This focused feature set reduces complexity and keeps the API fast and reliable. You do not need to learn a new JSON schema or endpoint structure.

curl https://api.cheapllmapis.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Transparent Pricing: No Hidden Fees or Subscriptions

Our pricing is straightforward and pay-as-you-go. Input tokens cost $0.15 per 1 million tokens, while output tokens are $0.50 per 1 million tokens. There are no monthly subscriptions, no tier locks, and no minimum spend requirements. You can top up with as little as $20 by crypto (USDT on TRC20, USDC on Base). We also offer bonus credits: +5% for deposits of $50, +10% for deposits of $100, and +15% for deposits of $200 or more. Your paid credit never expires, so you can pause usage without losing your balance. This model is ideal for developers who want to control costs precisely without committing to a monthly bill. It is not for you if you need SLA guarantees, SOC2 certifications, or on-prem deployment. We are an independent service, not a reseller of GPT or Claude.

from openai import OpenAI

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

Get Started Instantly with Free Trial Credit

You can test the API immediately without any commitment. New users get $0.50 of trial credit, one per person, valid for 7 days. Claim this credit with one click on your API key page. No credit card or phone number is required to start. You only need an email and a password to create an account. The API key is shown immediately after signup, allowing you to run your first request in seconds. This trial lets you verify compatibility with your existing stack before spending money. If you decide to continue, you can add prepaid credit with no expiration. We limit requests to 300 per minute per key and enforce an 8 MB request body limit. These limits are generous for most use cases while maintaining system stability.

import OpenAI from "openai";

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

High Performance: 100k Context Window & Streaming

The model supports a context window of 100,000 tokens, combining both the prompt and the completion. This allows you to pass large documents, codebases, or long conversation histories in a single request. Streaming is fully supported via Server-Sent Events, enabling you to display tokens as they are generated. This reduces perceived latency for end-users in chat applications. The API is designed for speed and efficiency, leveraging our own GPU infrastructure. We do not route your requests through multiple vendors, which can introduce variable latency. This direct path ensures consistent performance. If you need embeddings or image generation, this API is not for you. We focus solely on high-quality text completion.

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)

Privacy & Simplicity: No Card Required to Start

We keep your account setup simple and private. No phone number is required, and we do not use your prompts for training. This is important for developers who want to keep their data proprietary. Your API key can be regenerated at any time, instantly revoking the old one. This allows you to manage access securely without contacting support. We are an independent service, so you are not tied to a larger ecosystem. If you need a specific certification or compliance standard, check the requirements for your industry. For most developers, this API provides the simplicity and cost-efficiency needed to build AI-powered features quickly.

curl https://api.cheapllmapis.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Questions and answers

Is this a ChatGPT API alternative?

Yes, in the sense that it uses a compatible interface, but it is not GPT. We run our own open-weight model on our servers. It is not GPT, Claude, Gemini, Grok, or DeepSeek. You can use it as a drop-in replacement for OpenAI-compatible clients.

Do I need a credit card for the trial?

No. You only need an email and a password to get $0.50 of trial credit. Claim this credit with one click on your API key page. No credit card or phone number is required to start testing the API.

What is the pricing for input vs output tokens?

Input tokens are $0.15 per 1 million tokens. Output tokens are $0.50 per 1 million tokens. There are no monthly fees or minimum spend requirements.

Does the API support streaming?

Yes, we support streaming via Server-Sent Events (SSE). This allows you to receive tokens in real-time, which is essential for chat interfaces and improving user experience.

What is the context window size?

The context window is 100,000 tokens, which includes both the prompt and the completion. This is suitable for large documents and long conversations.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API keyRead the docs