Uncensored API

The abliterated llm API for uncensored outputs

Get an uncensored LLM that answers without refusals via a single OpenAI-compatible endpoint with a 100,000 token context window for direct, transparent usage.

100,000 token context window
No card needed for trial
Crypto top-up only

Get API key View documentation

Test with one call

curl https://api.llmabliterated.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Fix the syntax error in this python snippet"}]
  }'

from openai import OpenAI

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

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

Capabilities

OpenAI-Compatible

Works with existing SDKs by changing the base URL and key.

Streaming Support

Receive tokens via SSE with usage data in the final chunk.

JSON Mode

Enforce structured output using the response_format parameter easily.

Tool Use

Call functions and tools with standard tool_choice arguments.

No Refusals

The model answers controversial topics without unnecessary content gating.

Instant Access

Start using the API immediately after account creation and key generation.

Setup process

Create Account

Add Credit

Top up with crypto to receive bonus credit for larger amounts.

Send Request

Call the chat completions endpoint with the uncensored model ID.

Integration examples

Creative Writing

Generate unrestricted stories and narratives without content filters blocking details.

Agentic Workflows

Power agents that need consistent tool execution without refusal interruptions.

Data Extraction

Parse large documents efficiently using the extended context window capacity.

Dev Testing

Test integration logic with a reliable uncensored API endpoint easily.

Who builds with uncensored models and when to skip them

Developers building NSFW agents, roleplay bots, or creative writing tools prefer the abliterated LLM for its refusal-free outputs. Use it when content filters block your narrative logic. Skip it for standard enterprise tasks needing strict compliance. Our API handles 100,000-token contexts without extra routing fees. Simple integration suits builders who want direct access. Avoid this service if you require image generation or multimodal features, as we focus solely on text completion.

Why developers choose the abliterated LLM for NSFW tasks

We provide a single, uncensored model that answers without refusals for lawful adult use.

NSFW Content Generation

Our uncensored AI model generates explicit text without blocking adult themes.

Unrestricted Roleplay

Developers use this uncensored chatbot for complex character interactions without sudden refusals.

Content Filtering

Build your own moderation layers on top of a base model that does not filter.

Migrate from your current provider in three simple steps

Switch to the uncensored API by updating your base URL and API key. First, generate your key via Google or email on the Get API key page. Second, set base_url to HTTPS://api.llmabliterated.cc/v1 in your SDK. Third, send POST /v1/chat/completions with model "uncensored". The OpenAI-compatible interface handles the rest, eliminating complex routing.

How we differ from typical proxy and routing services

We serve one dedicated uncensored model, eliminating complex routing logic.

Feature	Us	Typical Proxy
Models	One specialized uncensored LLM	Multiple vendors
Infrastructure	Direct access, no middlemen	Opaque routing layers
Pricing	$0.15/$0.50 per million tokens	Variable markups

Visit the Get API key page and select Continue with Google or enter your email with a password.
Receive your single active key instantly; no phone number is required.
Configure your OpenAI-compatible SDK with base_url HTTPS://api.llmabliterated.cc/v1.
Send a POST request to /v1/chat/completions using model "uncensored".
Receive text output immediately, leveraging streaming support if needed.

Checklist for selecting an uncensored AI provider

Verify the service uses a single uncensored model, not a routed proxy. Check that prepaid crypto credit never expires. Ensure errors are free. Confirm the API is OpenAI-compatible. Look for no monthly fees. Verify privacy: prompts aren't used for training. Our API offers a 100,000-token context window with direct crypto top-ups.

Support Q&A

What is the abliterated LLM model?

It is an open-weight large language model hosted on our servers, designed to answer without content refusals for lawful adult use. It is a distinct model, not GPT, Claude, or Gemini, and uses the ID "uncensored" in requests.

Does the uncensored AI API support function calling?

Yes, the API supports function calling (tools and tool_choice) alongside streaming via SSE and JSON mode. You can manage parameters like temperature and top_p, but the service does not offer embeddings, image generation, or fine-tuning capabilities.

How much does the uncensored chatbot API cost?

Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. Errors and refusals are free, and prepaid credit never expires. You top up using crypto with bonuses ranging from 5% to 15%.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

What is the context window size?

The model supports a 100,000 token context window for both prompt and completion combined. You can request up to 16,000 output tokens per request, or 2,048 if you do not specify max_tokens.

Is the no filter AI service secure for private data?

Yes, we do not use your prompts for training. An account requires only an email address, and you can generate a new API key to replace an old one, ensuring your data remains private and accessible.

Obtain your key

Get API key