Uncensored LLM API

Unrestricted Character AI: The Uncensored LLM API

Get an open-weight uncensored LLM API with a 100,000 token context window, streaming support, and direct crypto pricing.

Get your key View documentation

100,000 token context window
Crypto top-ups from $20
$0.50 trial, no card

Test with one call

curl https://api.unrestrictedcharacterai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set the temperature to 0.7 for stable replies."}]
  }'

from openai import OpenAI

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

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

Core capabilities

OpenAI Compatible

Works with official SDKs by changing base_url and API key.

Streaming Support

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

Tool Calling

Execute functions with tools, tool_choice, and strict JSON mode.

Low Latency

High throughput infrastructure handles 300 requests per minute per key.

Privacy First

Prompts are not used for training your model data.

No Fluff

One model, one endpoint, transparent usage-based billing only.

Setup process

Create Account

Add Crypto

Top up with USDT or USDC for instant credit.

Send Request

Post to /v1/chat/completions with model id 'uncensored'.

Common integrations

NSFW Roleplay

Generate unrestricted adult content without artificial content filters.

Creative Writing

Write long stories with full context retention up to 100k tokens.

Data Extraction

Parse complex text with strict JSON mode for reliability.

Dev Tools

Integrate uncensored AI into your existing OpenAI-compatible applications.

Sign up: Use "Continue with Google" or email/password to create your account. The system generates a unique API key instantly, with no phone number required.
Top up: Add prepaid crypto credit via USDT (TRC20) or USDC (Base). Start with the free $0.50 trial or deposit a minimum of $20.
Call the API: Point your OpenAI-compatible SDK to our base URL and send requests to the "uncensored" model. Receive text responses immediately.

Unrestricted Character AI for NSFW and Beyond

Our unrestricted character AI delivers a single uncensored LLM API that removes refusals for adult, fictional, and controversial topics without compromising response quality.

NSFW Chatbot Applications

Integrate directly into your chatbot infrastructure. The model handles explicit dialogue naturally, supporting the full range of character interactions your users expect.

Uncensored AI for Research

Use the API for security research or content analysis. Get raw outputs without hidden filters interfering with your data integrity.

Unfiltered Chatbot Integration

Connect via the standard OpenAI-compatible endpoint. Send text in, get text out, and control the model with familiar parameters.

Migrate from OpenAI in Three Simple Steps

Switch your client configuration to our uncensored LLM API today. First, retrieve your API key from the dashboard. Second, update your base URL to HTTPS://api.unrestrictedcharacterai.com/v1. Third, set your model ID to "uncensored". All standard parameters like temperature and top_p remain compatible. You can immediately handle unrestricted chatbot scenarios without filter interruptions. Stop paying for refusals on lawful adult content and start streaming responses now.

Why Choose Us: 5 Signs of a True Uncensored API

We operate our own infrastructure, ensuring direct control over privacy and uncensored output without third-party routing. Our API follows standard OpenAI conventions, making migration effortless for existing chatbot applications. Pricing is strictly pay-as-you-go: $0.15 per million input tokens and $0.50 per million output tokens. We accept only crypto, eliminating payment friction and guaranteeing that prepaid credit never expires.

Feature	Our API
Infrastructure	Direct, self-hosted
Pricing	$0.15/$0.50 per 1M tokens
Payments	Crypto only
Credit	No expiration

The Developer’s Checklist for NSFW LLM Providers

Verify uncensored behavior

Test your API key with controversial prompts to confirm refusals are gone. Ensure the model handles adult themes without gatekeeping. Check token limits and streaming support. Confirm crypto-only payments and no hidden fees. Validate that your data stays private and isn't used for training. Avoid aggregators reselling other vendors' models. Ensure clear pricing per million tokens.

Real Cost Examples: Input, Output, and Streaming

Uncensored LLM API pricing is transparent and token-based. A typical 10k input, 1k output request costs $0.00165. Streaming via SSE works identically, so you pay for actual tokens generated, not estimates. Errors and refusals are free. Prepaid credit never expires, ensuring predictable costs for your NSFW chatbot without hidden fees or subscription surprises.

Common questions

What is unrestricted character AI and how does it work?

It is an uncensored LLM API. You send prompts via standard endpoints. The model answers without content refusals. It uses a single open-weight model. You pay per token. No subscriptions exist. Streaming is supported.

Does the uncensored AI model support streaming responses?

Yes. We support streaming via Server-Sent Events. Token usage appears in the final chunk. This reduces perceived latency. Your client handles partial updates. You get real-time output immediately. No waiting for full completion.

What is the context window size for requests?

The limit is 100,000 tokens total. This includes prompt and completion. You can output 16,000 tokens max. Default output is 2,048 tokens. Longer conversations fit easily. You retain full history context. No hard cuts occur.

Can I use function calling with this API?

Yes. We support tools and tool_choice. JSON mode is also available. You can define custom schemas. The model follows instructions strictly. This enables complex integrations. You control the output structure precisely. No extra fees apply.

Is the uncensored AI API compatible with OpenAI SDKs?

Yes. It uses the standard chat-completions endpoint. You just change the base URL. The official SDKs work directly. No custom wrappers are needed. You save integration time. Your existing code runs unchanged. Migration is instant.

How much does it cost per million tokens?

Input is $0.15 per million tokens. Output is $0.50 per million tokens. Errors are free. You pay only for usage. Prepaid credit never expires. No monthly fees exist. Crypto payments are accepted. Top-ups include bonuses.

Get your key now

Get your key