Uncensored API
Uncensored local llm API for Developers
Get a single uncensored local LLM endpoint with a 100,000-token context window, ready for any OpenAI-compatible client today.
$0.15per 1M input tokens
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
- 100,000-token context window
- No hidden subscriptions
- Crypto top-ups only
Test with one call
curl https://api.llmlocaluncensored.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Show me the current system uptime"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.llmlocaluncensored.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.llmlocaluncensored.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);Key features
OpenAI-Compatible
Works with official SDKs by changing base_url and key.
Function Calling
Supports tools, tool_choice, and JSON mode responses.
Streaming Support
Stream tokens via SSE with usage data in the final chunk.
Low Latency
Fast inference optimized for high-throughput developer workflows.
Simple Limits
300 requests per minute and 8 concurrent requests per key.
Privacy First
Prompts are not used for training your model data.
Setup guide
Create Account
Sign up with Google or email and get your key immediately.
Add Credit
Top up with USDT or USDC to start using the API.
Start Coding
Point your client to the base URL and send requests.
Use cases
NSFW Text Generation
Generate uncensored content without unexpected refusals for adult themes.
Creative Writing
Produce unrestricted fictional narratives and roleplay scenarios easily.
Data Processing
Parse large documents using the extensive 100,000-token context window.
API Integration
Drop this API into existing pipelines using standard OpenAI libraries.
uncensored local LLM for NSFW and Creative Workflows
The API delivers unrestricted text generation for adult and creative content without arbitrary refusals.
NSFW Prompt Enhancement
Feed text into the endpoint to expand detailed scenarios for video generation. The model preserves context without blocking mature themes.
Creative Writing Assist
Generate long-form stories with diverse character voices. Streaming responses let you read tokens as they arrive.
Roleplay Simulations
Maintain consistent personas over extended conversations. The 100k token window keeps your narrative logic intact.
Content Moderation Bypass
Get raw outputs for sensitive topics. Use the API to train your own filters without vendor bias.
Uncensored AI Cost Per Token: Real Math, No Guesswork
Concrete Token Arithmetic
Our uncensored AI API charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. A 5,000-token prompt with a 500-token response costs exactly $0.00075. Errors incur no charge, ensuring you pay only for delivered text. This transparent model eliminates hidden fees, making it a cheap LLM API for high-volume workflows.
Common Questions: Hardware, Context, and Models
The API handles inference remotely, so your local hardware specs like an RTX 3070 Ti or 8GB VRAM do not constrain throughput.
- Context Window: Supports 100,000 tokens total, with a 16,000 token maximum per response.
- Model Choice: We serve one uncensored open-weight model optimized for creative and NSFW workflows.
- Training: Currently, this is a raw generation endpoint without fine-tuning or embedding capabilities.
This setup eliminates complex model routing while ensuring you pay only for actual token usage.
Get Your API Key: Signup to First Token in Minutes
Create your account and receive your key instantly.
- Sign up via Google or email on the dashboard. No phone number required.
- Start with $0.50 trial credit valid for seven days. Credits never expire.
Copy your key into your client. Send requests to the OpenAI-compatible endpoint immediately.
Who Needs This API (And Who Should Skip It)
Developers needing strict, unfiltered text generation for NSFW or creative workflows get immediate access via our OpenAI-compatible endpoint.
Use it for prompt enhancement, roleplay engines, or research where refusals disrupt pipelines.
- Bring your own model context; we handle the serving.
- Pay only for tokens used, starting at $0.15 per million input tokens.
Skip if you need image generation, embeddings, or a dedicated UI, as we offer only raw API text output.
Checklist: How to Choose an Uncensored API Provider
Verify strict OpenAI compatibility. Our API uses standard endpoints like POST /v1/chat/completions, ensuring your existing code works without rewrites. Check the context window size. We offer 100,000 tokens for long-running sessions. Confirm pricing transparency. You pay per token, not a flat subscription. Ensure crypto top-ups are supported. We accept USDT and USDC with bonus credits. Look for clear rate limits. Our 300 requests per minute cap prevents unexpected throttling during high-volume tasks.
Frequently asked questions
What is the uncensored local LLM model ID for API requests?
The model ID is "uncensored". Send it in the JSON body to POST /v1/chat/completions. This open-weight model runs on our servers and answers without content refusals for lawful adult use.
How much does the uncensored AI API cost per token?
Input tokens cost $0.15 per 1M tokens, and output tokens cost $0.50 per 1M tokens. Errors and refusals are free. You pay exactly for what you consume with no hidden monthly fees.
Can I stream responses from the uncensored AI API?
Yes, streaming via Server-Sent Events is supported. Token usage details appear in the final chunk. You can also enable JSON mode or function calling tools within the same streaming request.
What is the context window size for the uncensored model?
The context window is 100,000 tokens for prompt and completion combined. The maximum output is 16,000 tokens per request, or 2,048 tokens if you do not explicitly set the max_tokens parameter.
How do I top up credits with crypto?
Top up with USDT (TRC20) or USDC (Base). Amounts range from $20 to $500. You receive a bonus credit of 5% at $50, 10% at $100, or 15% at $200.
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.
Get your key now
Sign up, copy your key, and update your base URL. That is all you need to do.
