Uncensored API

Gemma Abliterated API: Uncensored Text Generation

Get the uncensored LLM you need with prepaid crypto billing, 100k context, and no monthly fees for reliable text generation.

Get API key View documentation

$0.15 per 1M tokens input
Prepaid crypto billing only
100,000 token context window

Test via API

curl https://api.abliteratedgemma.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "fix syntax error in python loop"}]
  }'

from openai import OpenAI

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

import OpenAI from "openai";

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

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

Features

Uncensored Output
The model answers without refusals for lawful adult and creative use cases.
OpenAI Compatible
Drop-in replacement using standard chat-completions endpoints and SDKs.
Crypto Payments
Top up with USDT or USDC and get bonus credit automatically.
High Capacity
Process long documents with a 100,000 token context window limit.
Fast Streaming
Receive real-time responses via Server-Sent Events with token usage data.
Simple Limits
300 requests per minute and 8 concurrent connections per API key.

Setup process

Create Account
Sign in with Google or email to get your API key instantly.
Add Credits
Top up with crypto and receive bonus credit based on your amount.
Start Coding
Point your SDK to our base URL and send your first request.

Community projects

NSFW Chatbots
Deploy unrestricted conversational agents that do not refuse adult topics.
Creative Writing
Generate uncensored stories and scripts without content filters blocking creativity.
Data Extraction
Process large text documents efficiently with a massive 100k context window.
Research Testing
Test model behavior on controversial prompts without artificial refusal layers.

Move from another OpenAI-compatible provider in three steps

Switch without rewriting code

Update your base URL and API key, then keep your existing client code. First, grab your key on the dashboard. Second, set the new endpoint in your SDK config. Third, test a request. The model ID remains 'uncensored'. This works with any OpenAI-compatible library. You get a prepaid, uncensored LLM without changing your stack. Start with $0.50 trial credit today.

How this differs from a typical alternative on 6 concrete signs

We replace subscription lock-in with prepaid crypto billing and per-token pricing.

Feature	Typical Alternative	Ours
Billing	Monthly subscription	Prepaid crypto only
Hidden costs	Often higher output rates	Transparent input/output rates
Model focus	Multiple routed models	Single uncensored tuned model
Refusals	Standard moderation	Raw output for adult content
Credit expiry	Varies or resets	Never expires
Setup	Complex proxy setup	Drop-in OpenAI SDK

Gemma Abliterated: Uncensored Text Generation Use Cases

The gemma abliterated API delivers raw, refusal-free text generation for developers who need consistent, uncensored LLM output without subscription lock-in.

NSFW Chatbots
Generate unrestricted roleplay responses without sudden topic shifts or polite refusals blocking adult content.
Security Research
Elicit detailed answers on controversial or sensitive topics for jailbreak testing and model analysis.
Content Creation
Create unfiltered stories and scripts that maintain narrative tone without unnecessary editorializing.

A checklist for choosing a provider in this niche

Clear pricing: Verify per-token rates, like our $0.15 input and $0.50 output.
No subscriptions: Ensure prepaid credit never expires without monthly lock-in.
True uncensored: Confirm lawful adult content passes without arbitrary refusals.
OpenAI compatible: Check if standard SDKs work with a simple base_url change.
Crypto billing: Prefer providers accepting USDT or USDC for privacy.
Generous limits: Look for high RPM and 100k context windows.

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

Developers building NSFW chatbots or researchers testing refusal thresholds use our uncensored LLM for unrestricted text generation. It suits projects needing a single, tuned model without complex routing. However, it is not for teams requiring image generation, embeddings, or fine-tuning capabilities. If you need multi-vendor flexibility or strict enterprise SLAs, this direct API approach may not fit your workflow.

How it works: 3-5 numbered steps from signup to the first answer

Start generating uncensored text in under two minutes with these three simple steps.

Sign up instantly using your Google account or an email and password.
Receive your API key immediately; no phone number required.
Send your first request to POST /v1/chat/completions using the model ID uncensored.

Begin streaming responses or batch processing with your prepaid credit.

Common questions

What is the gemma abliterated model?

It is an uncensored large language model. The model id is "uncensored". It runs on our servers. You get text in, text out. No content refusals for lawful adult use. It does not block controversial topics.

How much does it cost per token?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors are free. Credit never expires. You pay only for real usage. No monthly fees or hidden costs apply to your account.

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 window is 100,000 tokens total. This includes prompt and completion. Max output is 16,000 tokens. You can set max_tokens. Streaming via SSE is supported. JSON mode is available for structured data.

Does it support function calling?

Yes. Tools and tool_choice are available. You can send JSON mode responses. Parameters like temperature and seed work. Streaming returns token usage. Use the standard OpenAI compatible endpoints for integration.

How many requests can I make?

You get 300 requests per minute. Only 8 requests run simultaneously. The body limit is 8 MB. One active key is allowed per account. A new key replaces the old one. Privacy is strict.

Generate your API key

Get API key

Gemma Abliterated API: Uncensored Text Generation

Test via API

Features

Uncensored Output

OpenAI Compatible

Crypto Payments

High Capacity

Fast Streaming

Simple Limits

Setup process

Create Account

Add Credits

Start Coding

Community projects

NSFW Chatbots

Creative Writing

Data Extraction

Research Testing

Move from another OpenAI-compatible provider in three steps

Switch without rewriting code

How this differs from a typical alternative on 6 concrete signs

Gemma Abliterated: Uncensored Text Generation Use Cases

NSFW Chatbots

Security Research

Content Creation

A checklist for choosing a provider in this niche

A checklist for choosing a provider in this niche

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

How it works: 3-5 numbered steps from signup to the first answer

How it works: 3-5 numbered steps from signup to the first answer

Common questions

Generate your API key