Uncensored LLM API
Unrestricted chat API for uncensored text generation
Get an unrestricted chat experience with our uncensored LLM API, processing a 100,000 token context window for just $0.15 per million input tokens.
- Prepaid crypto billing only
- 300 requests per minute
- No credit expiration ever
Test with one request
curl https://api.chatunrestricted.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List the three main endpoints for user authentication"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.chatunrestricted.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.chatunrestricted.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);Capabilities
OpenAI-Compatible
Drop-in replacement using the standard /v1/chat/completions endpoint.
Uncensored Model
Open-weight model tuned for lawful adult content generation.
Streaming Support
Full Server-Sent Events support with token usage tracking.
Function Calling
Native tools, tool_choice, and JSON mode capabilities.
No Subscription
Pay per token with no monthly fees or tiers.
Crypto Only
Top up via USDT or USDC with bonus credit.
Setup guide
Get Your Key
Sign up with Google or email to receive your key.
Add Crypto Credit
Top up with USDT or USDC to start using it.
Send Requests
Point your SDK to our base URL and start coding.
Common use cases
NSFW Content Generation
Generate explicit stories without content filters blocking your creative flow.
Roleplay Bots
Build characters that stay in context without moralizing your prompts.
Data Extraction
Parse large documents using the 100,000 token context window.
Dev Assistants
Use function calling to build tools that never refuse tasks.
Who uses this API and who should skip it
Developers building NSFW roleplay engines, adult content platforms, and uncensored data pipelines use this API for direct text generation without refusal gates. It fits teams needing raw model access via standard OpenAI-compatible endpoints. Skip it if you require image generation, embeddings, or fine-tuning capabilities. We do not offer model routing or multi-vendor aggregation. Also avoid us if you need strict enterprise compliance certifications like SOC2 or HIPAA, as we focus purely on unrestricted text output for lawful adult use cases.
Common mistakes in the uncensored niche and how to avoid them
Developers waste credits by ignoring context windows, causing unexpected refusals when tokens exceed 100,000. Others assume streaming returns accurate usage stats, yet our API only provides token counts in the final chunk. Avoid these errors by monitoring your 8 MB request body limits and setting explicit max_tokens to cap output at 16,000 tokens. Use the /v1/chat/completions endpoint strictly, as we do not offer embeddings or fine-tuning. This ensures predictable billing without hidden subscription tiers.
unrestricted chat: Use cases for NSFW, roleplay, and data
Our unrestricted chat API generates text without content refusals, enabling developers to build NSFW, roleplay, or raw data applications without fighting moderation filters.
NSFW Story Generation
Write explicit scenes without the model hedging or refusing adult themes. The uncensored LLM handles romantic or gritty narratives directly.
Roleplay Agents
Build characters that stay in context without breaking character due to safety triggers. This uncensored AI chat approach keeps interactions consistent.
Raw Data Extraction
Extract information without the model summarizing or softening controversial facts. The unrestricted GPT alternative provides direct, unfiltered outputs for your pipeline.
Real cost examples: How many tokens your budget buys
You pay only for actual usage at $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors and refusals are free. A $100 top-up covers roughly 666,666 input tokens or 200,000 output tokens. With a +15% bonus at $200, you get extended capacity for high-volume roleplay or data tasks. Credit never expires.
Migrate from another OpenAI-compatible provider in 3 steps
Switch your client configuration to our base URL and use the model id "uncensored" to start generating text without refusals immediately. First, update your base_url to point to our API endpoint. Second, replace your existing API key with the one generated on your dashboard. Third, verify connectivity by sending a simple request via the official OpenAI SDK. This process requires no code changes beyond the connection parameters, ensuring a smooth transition for your existing scripts.
How we differ from typical alternatives: 6 concrete signs
We replace subscription gates with prepaid crypto billing. This table shows how we differ from typical alternatives: 6 concrete signs.
| Feature | Typical Alternative | Ours |
|---|---|---|
| Billing | Monthly subscription | Crypto-only, prepaid tokens |
| Cost | $20–$30/mo flat | $0.15/$0.50 per 1M tokens |
| Content | Soft refusals | Uncensored, NSFW-friendly |
| Expiration | Monthly reset | Credit never expires |
| Refunds | Prorated only | Error adjustments |
| Contracts | Terms of Service | No hidden tiers |
Frequently asked questions
What is an unrestricted chat API and how does it differ from standard models?
It is an API endpoint that serves text without content refusals. You can send requests to POST /v1/chat/completions and receive responses for lawful adult use. Our model answers controversial topics directly without gating.
Does the uncensored LLM refuse NSFW or roleplay content?
No. The model is tuned to answer without refusals for lawful adult use. It processes your input and generates text freely. The only hard limit that always applies is no sexual content involving minors.
How much does the API cost per token?
Input tokens cost $0.15 per 1M and output tokens cost $0.50 per 1M. Errors and refusals are free. You pay only for real usage with prepaid credit that never expires.
Can I use the official OpenAI SDK to connect?
Yes. The API is fully OpenAI-compatible. You just change the base URL to HTTPS://api.chatunrestricted.com/v1 and provide your API key. It works with any standard OpenAI-compatible client.
How do I add credit to my account?
Top up using crypto only. We accept USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 is accepted. Payments are processed instantly with bonus credit available.
What is the maximum context window for requests?
The context window is 100,000 tokens for prompt and completion combined. You can set a max output of 16,000 tokens per request. Streaming via SSE provides token usage in the last chunk.
Generate your API key
Sign up, copy your key, and update your base URL. That is all you need to do.
