Code-First API

The Uncensored LLM API Built for Code

A hosted, OpenAI-compatible endpoint for the uncensored LLM model. Integrate unrestricted generation into your pipeline without managing GPUs or handling login walls.

Get API key Read the docs

OpenAI SDK compatible
64k context window
Crypto prepaid only

Try it in one request

curl https://api.abliterated.cc/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."}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.abliterated.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.abliterated.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: $0.25
Output tokens / 1M: $1.00
token context: 64,000
trial credit: $0.50
requests per minute: 300

What you get

OpenAI-Compatible

Works with official OpenAI SDKs and any compatible client. Change base_url and API key to start using the endpoint immediately.

Function Calling

Supports tools, tool_choice, and JSON mode. Stream responses or parse structured data just like you would with major cloud providers.

Large Context

64,000 token context window for long documents. Generate up to 16,000 tokens per request for complex code or reasoning tasks.

Predictable Pricing

Pay only for real token usage. Errors and refusals are free, and prepaid credit never expires with no monthly subscription.

Crypto Top-Up

Top up with USDT (TRC20) or USDC (Base). Receive bonus credit for larger deposits with no credit card required.

Direct Integration

No middlemen or routing layers. Connect directly to the abliterated model running on our servers for consistent performance.

How it works

Sign Up
Create an account with Google or email to receive your API key instantly.
Top Up
Add prepaid credit via crypto to start making requests immediately.
Integrate
Point your SDK to the base URL and start streaming responses.

What people build with it

Coding Agents

Integrate an uncensored coding LLM into your agent workflows. Generate code without refusals for unconventional or niche technical queries.

Data Extraction

Parse large documents with a 64k context window. Use JSON mode to extract structured data without format constraints.

Content Generation

Produce text without guardrails for lawful adult or controversial topics. Ideal for creative writing or specialized niche applications.

Research Tools

Build tools that analyze security research or political topics freely. The model answers without standard content filters.

Why Abliterated?

Most developers need an uncensored llm that behaves predictably. Standard models often refuse valid inputs based on subjective safety policies. Our hosted API serves a single, tuned model designed to answer without refusals for lawful adult use. This is not a chat interface or a catalog of models. It is a pure, code-first API experience. You get text in and text out. The model is tuned to handle controversial, sexual, or unconventional topics without blocking them. This makes it ideal for applications where content filtering is a bug, not a feature.

OpenAI-Compatible API

Use the standard OpenAI SDKs with zero code changes. Just update the base_url to https://api.abliterated.cc/v1 and set your API key. The endpoint supports POST /v1/chat/completions and GET /v1/models. You can stream responses via SSE, use function calling, and enforce JSON mode. Parameters like temperature, top_p, and seed work exactly as you expect. This is an uncensored llm online that fits into your existing infrastructure. No new libraries or complex integrations are required.

Code-First Integration

Designed for developers who prefer code over UI. Our uncensored ai models are accessible via standard HTTP requests. You can parse JSON responses directly into your application logic. The 64,000 token context window allows you to pass entire codebases or long documents. Max output is 16,000 tokens per request. If you need to stream data, the last chunk includes token usage. This is an uncensored ollama models alternative for production environments where you need reliability without the overhead of managing your own GPU cluster.

Uncensored by Design

The model is trained to answer without content refusals. It does not block standard adult topics or controversial political views. There is one hard content limit: sexual content involving minors is always refused. This is an uncensored coding llm that won't refuse valid code snippets just because they are unusual. You retain full control over how the output is used. No third-party moderation layers interfere with your requests. The model is open-weight and runs on our servers, ensuring consistent performance.

Transparent Pricing

Pay only for what you use. Input tokens are $0.25 per 1M, output tokens are $1.00 per 1M. Errors and refusals do not count toward your usage. Prepaid credit never expires, and there are no monthly fees. Top up with USDT (TRC20) or USDC (Base). Deposits between $50 and $100 get a 5% bonus, and $100+ get a 10% bonus. We do not accept cards, PayPal, or bank transfers. New accounts get $0.50 in trial credit valid for 7 days. No card is needed to start. Limits are 300 requests per minute and 8 concurrent requests per key.

Get Your API Key

Sign up with Google or email to get your key instantly. No phone number required. Your prompt data is not used for training. This is an api uncensored model built for speed and simplicity. One active key per account; generate a new key to replace the old one. Request bodies are limited to 8 MB. For detailed integration guides, check our documentation. Start building with an uncensored llm today.

Not For Everyone

This API is not for you if you need image, audio, or video generation. We do not offer embeddings, fine-tuning, or search capabilities. If you need multiple model choices or routing between different vendors, this is not the right service. We do not provide SLA guarantees, SOC2 certifications, or on-prem deployment options. If you require a chat website with a UI, look elsewhere. This is a raw API for developers. We do not claim benchmark scores or team sizes. If you need specific compliance for HIPAA or ISO standards, this may not fit your needs. We are an independent service, not a reseller of other vendors' models.

Questions and answers

What is the context window size?

The context window is 64,000 tokens, combining prompt and completion. You can generate up to 16,000 tokens per request. If you do not set max_tokens, the limit is 2,048 tokens.

Does it support function calling?

Yes, the API supports tools and tool_choice. You can also enforce JSON mode using response_format json_object. This works with the standard OpenAI SDK format.

How do I pay for the API?

We accept USDT (TRC20) and USDC (Base) only. You can deposit any whole amount from $10 to $500. Credit is charged by real token usage and never expires. No credit card is needed for the trial.

Is the model uncensored?

The model answers without refusals for lawful adult, fictional, or controversial topics. It does not block standard content. The only hard limit is sexual content involving minors, which is always refused.

What are the rate limits?

You are limited to 300 requests per minute and 8 concurrent requests per key. Request bodies must be under 8 MB. You get one active key per account.

Your key is one form away

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