Uncensored LLM API
NSFW models API for Developers
Deploy our uncensored LLM via OpenAI compatible API with 100,000 token context and zero refusals for lawful adult content.
- 100,000 token context window
- Crypto top-ups only
- $0.50 per 1M output tokens
Test with one call
curl https://api.modelsnsfw.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List all available nsfw model tiers and their monthly costs."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.modelsnsfw.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.modelsnsfw.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
Features
OpenAI Compatible
Use standard SDKs with our base URL and API key.
Streaming Support
Receive token usage data via SSE in the final chunk.
JSON Mode
Force structured output using response_format json_object easily.
Tool Calling
Enable function calling with tool_choice and tools parameters.
Zero Training
Your prompts are never used to train our models.
No Subscriptions
Prepaid credit never expires and costs nothing monthly.
Setup guide
Sign Up
Use Google or email to create your account instantly.
Get Key
Receive your API key immediately upon registration.
Top Up
Add crypto credit to start sending requests.
Common use cases
Uncensored Chatbots
Build chat interfaces that answer adult questions without filtering.
Roleplay Engines
Power immersive roleplay with a model that embraces any topic.
Content Generation
Create uncensored stories or scripts for adult audiences.
Data Processing
Analyze text with an uncensored LLM for specific domains.
How to Choose an Uncensored LLM Provider
Verify the endpoint is truly OpenAI-compatible. Our API uses standard /v1/chat/completions paths, ensuring immediate integration with existing SDKs without custom wrappers. Check if your prompts train the model. We never use your data for training, preserving your creative IP. Confirm pricing transparency. We charge $0.15 per million input tokens and $0.50 per output, with no hidden monthly subscriptions or phone number requirements. Ensure crypto-only top-ups fit your workflow, offering bonuses up to 15% on larger deposits.
NSFW models for Roleplay, Writing, and Data
We deliver uncensored text generation for adult roleplay, creative writing, and dataset creation without content filters.
Immersive Roleplay
Our open-weight model maintains character consistency and emotional nuance across long conversations. You get raw, unfiltered dialogue output suitable for complex narrative structures.
Creative Writing
Generate mature fiction without sudden refusals or policy gates. The API supports detailed scene descriptions and varied tones for adult storytelling.
Dataset Creation
Create large-scale training data for specialized models. Input your prompts and receive clean JSON or text outputs for fine-tuning.
Get Your API Key in 3 Steps
- Sign up with Google or email. No phone number required.
- Receive your API key immediately. Use it with the official OpenAI SDK by setting the base URL to our endpoint.
- Add crypto credit via USDT or USDC. Your prepaid balance activates instantly.
Send requests to /v1/chat/completions. The uncensored model responds with text. Start generating content without waiting for approvals.
Who Should Use This API (And Who Shouldn't)
Developers building NSFW chatbot applications or roleplay engines should use this API. Our uncensored LLM handles open-ended conversations without filtering lawful adult content, ensuring your users get consistent, unrefused responses. Use it for creative writing or data generation where standard models block specific topics. Do not use it if you need image generation, audio processing, or multi-model routing. We serve text only via a single endpoint.
- Best for: Custom NSFW LLM integrations.
- Not for: Users needing embedded vision or audio.
How We Differ From Aggregators and Gatekeepers
We provide a single, dedicated uncensored model via a standard OpenAI-compatible endpoint, ensuring total control over content policy for lawful adult use.
Real Questions from the Community
Developers want clear answers about model behavior and limits.
Does the uncensored LLM refuse lawful adult content? No. It answers without filtering for fiction, research, or controversy. The only hard limit is sexual content involving minors, which always gets refused.
What about context length? We support 100,000 tokens total. You can output up to 16,000 tokens per request. Errors are free. You pay only for real usage.
Is this an aggregator? No. We run one dedicated model. No routing. No training on your prompts. Just direct access.
FAQ
What are the best uncensored LLM options for NSFW models?
Our API serves one dedicated model id: uncensored. It outputs text without refusals. Input costs $0.15 per 1M tokens. Output is $0.50 per 1M tokens. You pay only for real usage. Errors are free.
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.
How do I top up my credit balance?
Use USDT on TRC20 or USDC on Base. Payments range from $20 to $500. You receive bonus credit for larger amounts. Your credit never expires.
Can I stream responses to reduce latency?
Yes. Enable streaming via Server-Sent Events. The final chunk contains usage data. This works with standard OpenAI SDKs. You can parse tokens in real time. It works for any client.
Does this uncensored AI model support function calling?
Yes. You can pass tools and tool_choice. Set response_format to json_object. Parameters like temperature and seed work. It supports structured output. Configure it like any OpenAI compatible endpoint.
What is the maximum context window size?
The limit is 100,000 tokens total. This includes prompt and completion. Max output is 16,000 tokens. Set max_tokens to control length. Requests over 8 MB are rejected. Plan your tokens carefully.
Get your key in one step
Sign up, grab your key, and update the endpoint. That is all.
