OpenAI Compatible
Use standard SDKs by changing base_url to our endpoint for instant integration.
Uncensored LLM Models
Uncensored llm models api for developers
Deploy a single uncensored LLM models endpoint with OpenAI compatibility, 100k context, and prepaid crypto billing starting at just $0.15 per million input tokens for reliable NSFW inference.
- OpenAI compatible chat-completions API
- 100,000 token context window
- Prepaid crypto billing only
Test the endpoint
curl https://api.uncensoredllmmodels.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate a list of 5 Python libraries for async web scraping"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.uncensoredllmmodels.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.uncensoredllmmodels.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
Capabilities
Zero Refusals
Answer without content filters for lawful adult, fiction, or controversial topics.
Large Context
Process 100,000 tokens total with up to 16,000 output tokens per request.
Tool Calling
Supports function calling, JSON mode, and streaming via SSE for automation.
Crypto Only
Top up with USDT (TRC20) or USDC (Base) with no cards needed.
No Expiry
Prepaid credit never expires, ensuring long-term value for your projects.
Setup process
Get Your Key
Sign up with Google or email to receive your API key immediately.
Add Crypto Credit
Top up via USDT or USDC to start making requests instantly.
Call the Endpoint
Send POST requests to /v1/chat/completions using your preferred OpenAI SDK.
Common integrations
Uncensored Coding AI
Execute automated tasks without base models recusing from standard operations.
NSFW Roleplay
Run unrestricted adult roleplay sessions without artificial safety layer blocks.
Data Analysis
Process large text inputs within the 100k context window efficiently.
Content Generation
Generate creative content that walks the line between uncouth and common.
uncensored LLM models for coding, roleplay, and automation
Uncensored LLM models deliver reliable inference without artificial refusals for your specific use cases.
Code Generation
Base models often refuse automated tasks or controversial logic. Our endpoint executes tool calls directly.
Roleplay
Generate unrestricted fictional content without safety filters blocking lawful adult themes or creative deviations.
Automation
Run 300 requests per minute with strict OpenAI compatibility, eliminating proxy configuration overhead.
migrate from openai-compatible providers in three steps
migrate from openai-compatible providers in three stepsSwitch to our uncensored LLM API by updating three configuration lines.
- Set your base_url to HTTPS://api.uncensoredllmmodels.com/v1.
- Replace your model ID with
uncensored. - Insert your new API key.
This single-model approach eliminates complex routing. You get strict OpenAI compatibility without proxy overhead. Start calling immediately with zero training data retention and no subscription friction.
Predictable uncensored API pricing with token math
Predictable uncensored API pricing with token math
Input tokens cost $0.15 per million; output tokens cost $0.50 per million. Errors and refusals incur zero charge, so wasted requests are free. A 10k prompt paired with a 2k response totals $0.002. Prepaid credit never expires, and crypto top-ups add bonuses starting at +5%. You pay only for what you consume.
from signup to first token in five steps
- Visit the "Get API key" page and choose "Continue with Google" or create an account with just an email.
- Receive your single active API key instantly; no phone number verification is required.
- Activate your $0.50 trial credit, which is valid for seven days and needs no card.
- Update your OpenAI SDK base_url to
https://api.uncensoredllmmodels.com/v1and set your key. - Send a POST request to
/v1/chat/completionswith model"uncensored"and receive your first token.
uncensored API vs traditional providers: 5 concrete signs
uncensored API vs traditional providers: 5 concrete signs
We deliver a single, uncensored model without complex routing or subscription friction. Traditional providers often refuse lawful adult or controversial topics, whereas our API serves uncensored LLM models that answer directly. Use this table to verify the differences in behavior and infrastructure.
| Feature | Traditional Providers | Our Uncensored API |
|---|---|---|
| Content Filtering | Aggressive safety layers | Zero refusals for lawful adult content |
| Pricing Model | Monthly subscriptions | Prepaid crypto only |
| Model Selection | Complex routing | Single optimized model |
what developers ask about uncensored AI models
Do they actually handle tool calling without refusals?
Yes. Our model executes function calls reliably, making it ideal for automation pipelines that traditional safe-tuned models often block during complex tasks.
Is this just for NSFW roleplay?
No. While it handles adult content, it is optimized for unrestricted coding, creative writing, and nuanced discussion without the typical safety guardrails.
How does the crypto pricing work?
We charge per token usage. Top up with USDT or USDC, and errors are free. Your credit never expires.
Support Q&A
What are uncensored LLM models used for?
They power unrestricted text generation for coding, roleplay, and automation. Our hosted API serves a single open-weight model tuned to answer without content refusals. You get text-in, text-out via standard endpoints without complex proxy configurations.
Does this uncensored API support function calling?
Yes. The API supports tools and tool_choice for precise function calling. It also handles JSON mode via response_format json_object. You can stream responses via SSE, but embeddings and image generation are not offered.
How much does the uncensored LLM API cost?
$0.15 per 1M input tokens and $0.50 per 1M output tokens. You pay for real usage; errors and refusals are free. There are no monthly fees, no subscriptions, and your prepaid credit never expires.
Can I use my existing OpenAI SDK?
Yes. It is fully OpenAI-compatible. Just change the base_url to HTTPS://api.uncensoredllmmodels.com/v1 and update your API key. The model id is uncensored. It works with any standard OpenAI-compatible client library.
What is the context window size?
The model supports 100,000 tokens for prompt and completion combined. You can request up to 16,000 tokens per output. If you omit max_tokens, the default output limit is 2,048 tokens per request.
How do I top up my credit?
Top up with crypto only: USDT (TRC20) or USDC (Base). Payments range from $20 to $500. You receive bonus credit for higher amounts, such as +10% for $100 or +15% for $200.
Access via API key
Register, retrieve your key, and update your base URL. That is the complete configuration.
