OpenAI Compatible
Use official SDKs by changing the base URL to our endpoint.
Raw LLM Infrastructure
Uncen.com: The Uncensored LLM API
Generate uncensored text with a single API call. Get your first token in seconds using our 100,000 token context window.
- 100,000 token context window
- OpenAI-compatible chat API
- Crypto top-ups only
Test with one call
curl https://api.uncencom.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.uncencom.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.uncencom.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
No Content Refusals
The model answers controversial or adult topics without standard corporate guardrails.
Streaming & JSON
Supports SSE streaming and strict JSON mode for reliable parsing.
Simple Pricing
Pay only for tokens used; errors and refusals cost zero credits.
Crypto Payments
Top up with USDT or USDC; no bank transfers or cards.
Instant Access
Get your API key immediately after signing in with Google or email.
Setup process
Get Your Key
Sign up with Google or email to receive your API key instantly.
Set Base URL
Configure your client to point to HTTPS://api.uncencom.com/v1.
Send Requests
Call POST /v1/chat/completions and receive raw text responses immediately.
Use cases
Uncensored Chatbots
Build character-driven bots that answer any question without moralizing.
Content Generation
Generate raw text for NSFW stories or unfiltered creative writing projects.
Data Processing
Extract structured JSON data without the model refusing due to format.
Research Models
Test how large models handle controversial topics without external filters.
From Signup to First Token in 60 Seconds
Get your key instantly and start generating raw text immediately.
- Sign up via Google or email; no phone number required.
- Receive your API key on the dashboard.
- Update your SDK base_url to
https://api.uncencom.com/v1. - Send a POST request with model
uncensored.
Pay only for tokens used.
Why Developers Choose uncen.com for Raw Output
We deliver consistent, filter-free text generation by stripping corporate guardrails from standard inference pipelines.
NSFW Chatbot Infrastructure
Generate unlimited adult content without unexpected refusals or soft-blocks disrupting your user experience.
Unhinged AI Agents
Run creative roleplay bots that maintain character voice across long context windows without moralizing.
Uncensored LLM Data
Extract raw training data or raw answers for projects needing unfiltered model behavior.
Stop Fighting Filters: Common Uncensored API Mistakes
Developers often misconfigure max_tokens, triggering unexpected truncation when generating long narratives. Ensure your payload sets this limit explicitly to avoid cutting off creative output mid-sentence. Another frequent error involves ignoring the 100,000-token context window, causing older conversation history to vanish prematurely. Always account for both prompt and completion usage to maintain coherence. Additionally, verify that your client handles streaming responses correctly, as token usage details appear only in the final chunk, preventing accurate billing tracking if overlooked.
Switch Your Base URL: The Three-Step Migration
Switch Your Base URL: The Three-Step Migration
Update your base URL and API key to route raw, uncensored responses immediately.
- Generate a new key on the dashboard.
- Set
base_urltohttps://api.uncencom.com/v1. - Point requests to the
uncensoredmodel.
This simple shift replaces strict corporate guardrails with direct output. You retain all existing SDK compatibility while accessing unrestricted generation.
The Uncensored Provider Checklist
Verify the model refuses nothing for lawful adult use before committing.
- Confirm it is a dedicated uncensored LLM, not a filtered reroute.
- Check for a strict child safety limit.
- Ensure the API is OpenAI-compatible for easy SDK integration.
- Validate prepaid credit with no monthly fees.
- Confirm crypto-only top-ups via USDT or USDC.
- Verify a $0.50 trial requires no card.
Signal vs. Noise: How We Differ
Our API delivers raw, uncensored output without hidden refusal logic or corporate guardrails. We provide a single, open-weight model optimized for unfiltered generation, not a routed abstraction layer. Unlike platforms bundling embeddings or fine-tuning, we offer exactly what you need: straightforward chat-completions. This focused infrastructure ensures you control every token, avoiding the noise of unnecessary features that complicate simple text generation workflows.
| Feature | Our API | Typical Alternative |
|---|---|---|
| Content Logic | None (Uncensored) | Hidden filters |
| Model Scope | Single uncensored model | Routed multi-model |
| Extra Features | None | Embeddings, vision, etc. |
Frequently asked questions
What is uncen.com and how does it work?
It is an API provider. You send text and get text. The service uses a single uncensored model. It accepts standard OpenAI formats. You pay by token count. Errors cost nothing. Your data stays private. This is the core function.
Does the uncensored LLM refuse standard adult topics?
No. It answers freely. Only child content gets blocked. The model ignores most filters. You get raw output. This works for adults. Use it for stories. Or use it for research. The model does not lecture you. It just generates text.
What is the context window size for requests?
It holds 100,000 tokens. This covers input and output. You can send large prompts. The model remembers details. This helps long tasks. Keep responses under 16,000 tokens. Streaming works well. This limit supports deep analysis. You get full context.
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 price per million tokens?
Input costs $0.15 per million tokens. Output costs $0.50 per million tokens. Pay only for usage. No monthly fees. Errors are free. Credits never expire. This pricing is transparent. You control your spend. This is straightforward.
Can I use my existing OpenAI SDK?
Yes. Change the base URL. Use api.uncencom.com/v1. Send the new API key. The format matches exactly. Streaming works fine. Tools and JSON mode work. You switch easily. No code changes needed. This is simple.
Generate your API key
Register, retrieve your key, and update your base URL. That’s all you need.
Start now
https://api.uncencom.com/v1