Uncensored LLM API
Uncensored llm api for developers
Deploy a robust uncensored LLM API for your NSFW chatbot with 100,000 tokens context window, prepaid billing, and no monthly subscription lock-in.
- 100,000 token context window
- $0.15 per 1M input tokens
- OpenAI-compatible chat endpoint
curl https://api.apillmuncensored.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List the top five features of this api."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.apillmuncensored.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.apillmuncensored.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
Core features
OpenAI-Compatible
Works with standard OpenAI SDKs by changing base_url.
Streaming Support
Get real-time token usage via Server-Sent Events.
Function Calling
Use tools and tool_choice for complex logic.
JSON Mode
Force structured output with response_format json_object.
Prepaid Credit
Pay only for tokens used, no expiry.
Crypto Top-up
Add funds via USDT or USDC only.
Setup guide
Create Account
Sign up with Google or email instantly.
Get Key
Receive your API key immediately on screen.
Send Request
Post to the chat completions endpoint.
Community projects
NSFW Chatbots
Enable adult content without arbitrary refusals.
Roleplay Apps
Maintain character consistency over long sessions.
Creative Writing
Generate stories with full creative freedom.
Content Generation
Produce uncensored text for various media.
1. The uncensored API buyer's checklist: 6 checks for reliability
Verify strict OpenAI compatibility, true abliteration models, and transparent token billing. Confirm 100k context windows, crypto top-ups, and real-time usage tracking. Ensure no subscription lock-in, predictable costs, and dedicated endpoints. Avoid providers with hidden fees or limited streaming support. Test function calling and JSON modes before committing. Check for immediate key generation and clear refund policies. Prioritize services with minimal content restrictions for lawful adult use.
2. uncensored LLM API: use cases for NSFW, roleplay, and creative writing
Our uncensored LLM API powers NSFW chatbots and roleplay apps by refusing nothing on lawful adult content, delivering consistent character voices without moral lectures.
NSFW Chatbots
Deploy roleplay bots that generate unrestricted dialogue, maintaining character consistency across 100,000-token contexts without unexpected refusals.
Creative Writing
Generate stories with mature themes, ensuring the model outputs raw narrative data without filtering nuanced emotional or physical descriptions.
Content Generation
Build tools that produce unfiltered text for adult audiences, leveraging streaming SSE for real-time token delivery in high-traffic apps.
3. Get your key and send your first request
How it works: from signup to your first API response in 3 steps
- Sign up with Google or email. No phone number needed. Get your API key instantly.
- Add $0.50 trial credit. It lasts seven days. You can upgrade to crypto later.
- Send a POST request to the chat-completions endpoint. Use the model ID "uncensored". Receive text output immediately. That is all.
4. Common mistakes: why 'unhinged' models fail in production apps
4. Common mistakes: why 'unhinged' models fail in production apps
Models fail because they lack structural discipline, not just filters.
- Missing JSON mode: without
response_format: {"type": "json_object"}, parsers crash on stray commas. - Ignoring context windows: sending 100k tokens blindly drains prepaid credits and truncates history.
- No rate limiting: exceeding 300 requests per minute triggers hard 429 errors.
Always implement retry logic with exponential backoff to handle network jitter gracefully.
5. Who uses our API and who should look elsewhere
Developers building NSFW chatbots and roleplay apps should use this API. It handles uncensored text generation without refusals for lawful adult content. Teams requiring image or audio capabilities should look elsewhere, as we serve text only. If you need embeddings, fine-tuning, or multi-model routing, this single-model endpoint is not for you. Our API suits projects prioritizing low latency and predictable billing over diverse model options.
Real cost examples: token math for your NSFW chatbot project
Predictable billing starts with precise token arithmetic. Your NSFW chatbot costs $0.15 per million input tokens and $0.50 per million output tokens. A 10,000-token conversation costs roughly $0.65 total. You never pay for errors. Crypto top-ups add bonus credits automatically. Track usage in real-time to keep overhead minimal. No hidden monthly fees. No subscription lock-in. Pay only for what you use.
Common questions
What is the uncensored LLM API model id and context window?
The model id is "uncensored" with a 100,000 token context window. It runs on our servers, not as GPT or Claude. You can send requests using standard OpenAI-compatible SDKs by setting the correct base URL and model identifier in your configuration.
Does the API support function calling and JSON mode?
Yes, it supports both function calling and JSON mode. You can use tool_choice and set response_format to json_object. These features allow your application to parse structured data reliably without needing external parsing libraries or complex prompt engineering for specific formats.
How much does it cost per million tokens?
Input tokens cost $0.15 per million and output tokens cost $0.50 per million. Errors and refusals are free. This transparent pricing ensures you only pay for actual token usage, with no hidden fees or monthly subscription lock-in required for access.
What payment methods are accepted for topping up credit?
We accept only USDT on TRC20 or USDC on Base. The minimum top-up is $20 and the maximum is $500.
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 are the request limits per API key?
You can send 300 requests per minute and have 8 concurrent requests at once. The maximum request body size is 8 MB. These limits ensure stable performance for your NSFW chatbot or roleplay application without requiring complex rate-limit management on your end.
