No Filters. No Friction.
Uncensored-llm.vercel.app: The Uncensored AI API
Get an open-weight uncensored LLM API endpoint with a 100,000 token context window for unrestricted creative writing and NSFW generation.
OpenAI-compatible API, zero refusals.
Test with one request
curl https://api.uncensoredllmvercelapp.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.uncensoredllmvercelapp.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.uncensoredllmvercelapp.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);https://api.uncensoredllmvercelapp.com/v1uncensored
OpenAI-compatible POST endpoint
$0.15 per 1M input tokens
100,000 token context window
Core capabilities
True Uncensored Output
Our single model answers without corporate policy filters for lawful adult content.
High Throughput
Optimized for speed with 300 requests per minute and streaming via SSE.
Crypto Prepaid Credits
Pay with USDT or USDC; credits never expire and errors are free.
Developer First SDKs
Works with official OpenAI SDKs by simply changing the base URL and key.
Advanced Parameters
Supports function calling, JSON mode, temperature, and seed for precise control.
Instant Access
Sign up with Google or email to get your API key immediately.
Setup workflow
Get Your Key
Sign in with Google or email to receive your unique API key instantly.
Top Up Crypto
Add credits using USDT or USDC with bonus tiers starting at $50.
Send Requests
Point your client to our endpoint and start generating unrestricted text data.
Common use cases
NSFW Roleplay
Generate explicit fictional narratives without unexpected refusals or content policy interruptions.
Creative Writing
Write stories with mature themes and controversial topics without corporate moderation.
Data Generation
Create large datasets of uncensored text for training or analysis purposes.
Research & QA
Test model behavior on edge cases without bias from standard safety filters.
Switch from OpenAI in three steps
Start using our uncensored LLM API immediately by updating your base URL.
Change
base_urltohttps://api.uncensoredllmvercelapp.com/v1.Replace your API key with the one from your dashboard.
Send requests to
/v1/chat/completionsusing modeluncensored.
Our openai compatible API handles standard parameters like temperature and streaming.
Get unrestricted output without modifying your existing code structure.
uncensored-llm.vercel.app for NSFW and creative workflows
The uncensored-llm.vercel.app API delivers unrestricted text generation for NSFW roleplay, creative writing, and explicit content without policy filters.
NSFW Roleplay
Generate detailed adult scenarios with a 100,000-token context window, ensuring consistent character voices across long interactions.
Creative Writing
Produce unrestricted narratives that bypass typical corporate moderation, allowing full creative freedom for your stories.
Uncensored Data Generation
Output raw, unfiltered text for datasets requiring diverse or explicit language, backed by a transparent, crypto-only prepaid credit system.
How we differ from typical providers
We strip away corporate moderation and complex routing. Unlike aggregators, we serve a single, optimized uncensored model with transparent crypto-only payments. You pay $0.15 per million input tokens and $0.50 per million output tokens. Errors are free. This single-model approach ensures high throughput and true unrestricted output for your NSFW and creative workflows.
From signup to first token in minutes
Get started in five steps
- Sign up with Google or email. We show your API key immediately.
- Add crypto credit via USDT or USDC.
Who it’s for and who it isn’t
Developers building NSFW roleplay engines, creative writing tools, or uncensored data pipelines use our API. It suits teams needing high-throughput, unrestricted text output without policy filters. You need a simple, OpenAI-compatible endpoint for lawful adult content generation. It is not for enterprises requiring embeddings, image generation, or fine-tuning. If you need model routing or SLA guarantees, look elsewhere. This single-model API strips away complexity.
Checklist for choosing an uncensored provider
Verify the endpoint structure matches OpenAI standards to ensure quick SDK integration without custom client code. Confirm the context window supports your long-form creative or research needs, ideally 100k tokens or higher. Check that pricing is transparent and based on actual token usage rather than opaque subscriptions. Ensure the provider uses a prepaid credit system where funds never expire. Finally, confirm that refusals are rare and limited only to specific content like minors, not broad policy filters.
Frequently asked questions
What is uncensored-llm.vercel.app?
It is a hosted OpenAI-compatible API serving a single uncensored model. Text in, text out. No embeddings, images, or video generation. It strips away routing complexity for direct, unrestricted output.
How do I get started with the uncensored API?
Sign up with Google or email, then receive your API key immediately. Use the base URL HTTPS://api.uncensoredllmvercelapp.com/v1 in your client. Send requests to POST /v1/chat/completions to start generating text.
Does the uncensored model filter NSFW content?
Yes, it removes most refusals for lawful adult content. The only hard limit is sexual content involving minors. You get unrestricted outputs for creative writing, roleplay, and controversial topics without policy friction.
What are the token limits for requests?
The context window supports 100,000 tokens total. Max output is 16,000 tokens per request, or 2,048 if you do not set max_tokens. This allows deep context analysis for long-form generation tasks.
How does the prepaid credit system work?
Credit is charged by real usage; errors are free. Top up with USDT (TRC20) or USDC (Base). Credits never expire. You get bonus credit for larger deposits, starting with +5% from $50.
Can I use the official OpenAI SDKs?
Yes, it is fully OpenAI-compatible. Change the base_url and API key in your client. Support includes streaming via SSE, JSON mode, and function calling for seamless integration into your existing codebase.
Retrieve your API key
Register, copy the token, and update your base URL. That’s it.
