Uncensored AI API

Locally uncensored ai api

Get a single, uncensored LLM API with transparent prepaid credits and crypto billing. Enjoy raw inference costs starting at $0.15 per 1M input tokens, with no per-token surprises or hidden egress fees.

Get API key View API reference

OpenAI-compatible POST /v1/chat/completions endpoint
Prepaid crypto billing with no subscriptions
No training on your prompt data

Test in one call

curl https://api.uncensoredlocally.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.uncensoredlocally.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.uncensoredlocally.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

Core capabilities

Uncensored Inference
Answer without content refusals for lawful adult use.
Prepaid Credits
Paid credit never expires and errors are free.
Crypto Only
Top up via USDT or USDC with bonus credit.
OpenAI Compatible
Works with official SDKs by changing the base URL.
100k Context
Supports a 100,000-token context window for long tasks.
No Training
Your prompts are not used to train the model.

Setup guide

Create Account
Sign up with Google or email to get your key.
Add Credits
Top up with crypto to start using the API.
Start Coding
Point your client to our base URL and send requests.

Built with this API

NSFW Content Generation
Generate unrestricted adult content without sudden content filters blocking output.
Creative Writing
Write stories with controversial themes without model refusal interruptions.
Security Research
Probe model boundaries for jailbreaks without paying for refusals.
Data Annotation
Label large datasets with an uncensored model for training.

Why Most 'Unrestricted' APIs Lie About Their Limits

Most providers hide egress fees behind 'unrestricted' labels, charging you heavily just to read the output. Our uncensored AI API charges only for raw inference: $0.15 per 1M input tokens and $0.50 per 1M output tokens. We do not resell other vendors' models; we run our own open-weight model. Errors are free. No subscriptions. You pay for the tokens you use, with prepaid credit that never expires. This is transparent pricing for developers who hate surprises.

locally uncensored: 4 Use Cases for Uncensored AI

The locally uncensored API delivers raw inference without content filters, allowing developers to deploy models that answer any lawful topic without refusal.

NSFW Content Generation

Generate adult-themed narratives or roleplay scenarios without hitting artificial guardrails that block standard models.

Uncensored AI Chatbots

Build conversational agents that retain context and personality, ignoring polite refusals on controversial subjects.

Uncensored LLM Leaderboard Testing

Test model capabilities on edge-case prompts where censorship typically reduces output quality.

Uncensored Deepseek Alternatives

Use our single model for tasks requiring unfiltered data processing, avoiding the training biases of major providers.

The 6-Point Checklist for Choosing an NSFW LLM Provider

Verify explicit NSFW tolerance without hidden filters. Check for transparent, prepaid billing to avoid per-token surprises. Ensure OpenAI compatibility for easy SDK migration. Confirm your prompts stay private and aren’t used for training. Look for crypto-only top-ups with bonus credit. Avoid providers charging for errors or refusals. Our API delivers raw inference at $0.15/$0.50 per million tokens with zero training on your data.

How Our Uncensored API Differs from Standard Providers

Transparent Inference Costs

Our uncensored API charges only $0.15 per million input tokens and $0.50 per million output tokens. We bill strictly by actual usage with prepaid credit, ensuring no hidden egress fees or complex subscription traps. This transparent pricing model allows developers to predict costs accurately without surprise charges for unused capacity or data egress.

Feature	Our API	Standard Providers
Billing Model	Prepaid, per-token	Subscription + usage
Content Limits	Uncensored (adult)	Varies by tier
Privacy	No training on prompts	Often trains data

Start generating text in under two minutes using your new uncensored API.

Get your key. Sign up via Google or email to receive an API key immediately.
Load credits. Top up with crypto; all credits never expire.
Configure your client. Point your OpenAI-compatible SDK to our base URL.
Send your first prompt. Use the uncensored model ID to receive unrestricted outputs.

Migrate Your OpenAI Compatible App in Three Steps

Update your base_url to https://api.uncensoredlocally.com/v1 in your existing client configuration.
Set the model parameter to uncensored for every request.
Replace your current API key with the new key from your dashboard.

This simple change activates a 100,000-token context window without altering your code logic.

Common questions

View API reference

What is the locally uncensored API?

It is a hosted, OpenAI-compatible chat-completions API serving one uncensored large language model. You get text in, text out via standard endpoints with no content refusals for lawful adult use.

Does it support streaming responses?

Yes. We support streaming via Server-Sent Events (SSE). You can access token usage details in the last chunk of the stream, ensuring you see real-time consumption as the model generates text.

Is there a monthly subscription fee?

No. We charge only for real token usage with prepaid credit. Errors and refusals are free, and your paid credit never expires, so you only pay for what you actually consume without hidden fees.

Can I use JSON mode?

Yes. You can set the response_format parameter to json_object to force structured output. This ensures consistent parsing for your applications without needing complex prompt engineering to strip markdown from the generated text.

How much context window does it have?

It supports a 100,000 token context window for both prompt and completion together. You can set a max output of 16,000 tokens per request, or use the default 2,048 tokens if you do not specify one.

Do you train on my prompts?

No. Your prompts are not used for training data. We respect your privacy and use only your email for account creation, ensuring your conversation history remains private and is not repurposed for model improvement.

Get your API key now

Get API key View API reference

Locally uncensored ai api

Core capabilities

Uncensored Inference

Prepaid Credits

Crypto Only

OpenAI Compatible

100k Context

No Training

Setup guide

Create Account

Add Credits

Start Coding

Built with this API

NSFW Content Generation

Creative Writing

Security Research

Data Annotation

Why Most 'Unrestricted' APIs Lie About Their Limits

locally uncensored: 4 Use Cases for Uncensored AI

NSFW Content Generation

Uncensored AI Chatbots

Uncensored LLM Leaderboard Testing

Uncensored Deepseek Alternatives

The 6-Point Checklist for Choosing an NSFW LLM Provider

How Our Uncensored API Differs from Standard Providers

Transparent Inference Costs

From Signup to First Token: How It Works

Migrate Your OpenAI Compatible App in Three Steps

Migrate Your OpenAI Compatible App in Three Steps

Common questions

Get your API key now