Uncensored LLM API
OpenRouter nsfw model: uncensored API alternative
Skip OpenRouter filtering: get a direct uncensored LLM API with a 100k token context window, designed for developers who need reliable NSFW generation without hidden refusals.
- 100k token context window
- No hidden content filters
- $0.15 per 1M tokens
Claim trial keyView documentation
curl https://api.openrouternsfwmodel.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List the top 5 HTTP status codes"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.openrouternsfwmodel.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.openrouternsfwmodel.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);Core features
- openrouternsfwmodel.com › 01
OpenAI Compatible
Drop-in replacement for standard SDKs using the same base URL structure.
- openrouternsfwmodel.com › 02
Streaming Support
Full SSE streaming with token usage details included in the final chunk.
- openrouternsfwmodel.com › 03
Function Calling
Native tool support with flexible choices for complex application workflows.
- openrouternsfwmodel.com › 04
JSON Mode
Enforce structured output using response_format for reliable data extraction.
- openrouternsfwmodel.com › 05
Crypto Payments
Top up with USDT or USDC and receive bonus credit on deposits.
- openrouternsfwmodel.com › 06
Simple Limits
300 requests per minute per key with 8MB request body limits.
Setup guide
Get Your Key
Sign up with Google or email to receive your API key instantly.
Configure Client
Update your base URL to point to our dedicated uncensored endpoint.
Send Requests
Start generating text using the standard chat completions endpoint structure.
Use cases
Roleplay Integration
Connect directly to tools like Silly Tavern for uncensored character interactions.
Content Creation
Generate unrestricted narratives without worrying about standard model content filters.
API Testing
Validate your OpenAI-compatible client code against a reliable uncensored endpoint.
Custom Workflows
Build applications requiring specific tone or topic freedom without refusals.
Why choose an openrouter NSFW model over standard APIs
Use an openrouter NSFW model when you need consistent, unfiltered responses without third-party routing delays or unexpected content filters.
Dedicated Endpoint
A single uncensored LLM endpoint eliminates routing complexity and ensures predictable token pricing for every request.
Zero Hidden Filters
Lawful adult content passes through without artificial refusals, making it ideal for NSFW chatbot scenarios.
Predictable Costs
Transparent token usage means you only pay for what you consume, with no hidden subscription fees.
Direct Access
Connect directly to our servers using standard OpenAI SDKs, avoiding aggregator latency and variability.
Who uses this API and who should skip it
RP developers and fiction writers seeking a reliable uncensored LLM for Silly Tavern or Janitor AI.
- Use it for direct NSFW chatbot integration without content refusals.
- Skip if you need image, audio, or video generation, as we serve only text.
- Avoid if you require model routing between vendors or fine-tuning capabilities.
This single open-weight model handles 100,000-token contexts, eliminating aggregator complexity for predictable NSFW output.
Your pre-integration checklist for uncensored LLMs
Verify the API returns standard OpenAI JSON structures to ensure immediate compatibility with your existing client.
- Confirm the context window supports your narrative length (e.g., 100k tokens).
- Check that streaming via SSE is available for real-time token display.
- Ensure function calling works if your RP tool uses tools.
- Verify pricing is transparent per 1M tokens, with no hidden filtering fees.
- Confirm the model id is simple (e.g.,
uncensored) and not a complex routing string.
Real token cost examples for NSFW generation
Predictable NSFW chatbot pricing
Our uncensored LLM costs $0.15 per million input tokens and $0.50 per million output tokens.
- A 10k input prompt generating 2k tokens costs roughly $0.0013.
- Streaming responses include real-time token usage data in the final chunk.
Errors remain free, ensuring you pay only for actual text generated. This transparent structure eliminates hidden fees for your roleplay scripts.
How our uncensored API differs from aggregators
Our uncensored API eliminates routing complexity by serving a single, dedicated model with transparent pricing. Unlike multi-model aggregators, we offer direct access to an open-weight endpoint without hidden filters or unexpected content refusals. This approach ensures predictable NSFW performance for developers who need reliability. The table below highlights key distinctions between our dedicated service and typical aggregation platforms.
| Feature | Our Dedicated API | Typical Aggregator |
|---|---|---|
| Model Selection | Single uncensored model | Multiple vendor models |
| Routing | Direct endpoint | Complex routing logic |
| Pricing | Transparent token cost | Variable markups |
| Content Policy | No hidden filters | Vendor-dependent filters |
Migrate your OpenAI-compatible client in 3 steps
Switch to our uncensored API by updating your base URL and model ID.
- Point your client to HTTPS://api.openrouternsfwmodel.com/v1.
- Set the model ID to "uncensored".
- Replace your API key with the one from your account.
Standard OpenAI SDKs work immediately. You gain access to a 100,000-token context window without content refusals.
FAQ
What is the openrouter NSFW model API?
It is a hosted chat-completions endpoint serving one uncensored large language model. Text in, text out. We do not route between vendors or serve other companies' models. Our API works with standard OpenAI SDKs. We provide a direct, open-weight model endpoint without hidden filters. Streaming and function calling are supported.
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 much does it cost to generate content?
Input tokens cost $0.15 per 1 million tokens. Output tokens cost $0.50 per 1 million tokens. You pay for what you use. Prepaid credit covers usage. No monthly fees apply. The model id is uncensored. Context window supports 100,000 tokens total. Max output is 16,000 tokens per request.
Can I use this with Silly Tavern or Janitor?
Yes. It is an OpenAI-compatible API. Change the base URL to api.openrouternsfwmodel.com/v1. Set the API key from your dashboard. Use model id uncensored. Parameters like temperature and top_p work. Streaming via SSE is supported. JSON mode is available. Function calling works too.
Are there any hidden content filters?
No. The model is tuned to answer without content refusals for lawful adult use. A hard limit prevents sexual content involving minors. Requests violating this are refused. Prompts are not used for training. Privacy is maintained. You control the context. Errors are free. Streaming works.
How do I pay for credit?
Crypto only. Accept USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 works. Bonus credit is added at thresholds. Sign up with Google or email. The API key shows immediately. Support is available for double charges.
Get your API key in one step
Sign up, copy the key, update the base URL. Done.
