One Uncensored LLM API
One Uncensored LLM API for Developers
Drop-in OpenAI-compatible endpoint for a single, dedicated uncensored model. Change your base_url and key, keep the code.
One uncensored API, drop-in compatible.
Try it in one request
curl https://api.onekeyllmapi.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.onekeyllmapi.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.onekeyllmapi.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);- 100k context window
- $0.15 per 1M input tokens
- No vendor lock-in
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
What you get
Drop-In Compatibility
Works with official OpenAI SDKs by changing only the base_url and API key. No code rewrites required.
Single Dedicated Model
We do not route across dozens of vendors. You get one uncensored open-weight model tuned for lawful adult use.
No Extra Costs
Pay-as-you-go prepaid credit. No monthly fees, no subscriptions, and paid credit never expires.
Streaming & Tools
Supports SSE streaming and tool/function calling via the standard chat-completions endpoint.
Transparent Limits
300 requests per minute per key. 8 MB request body limit. Simple, predictable constraints.
Privacy First
Prompts are not used for training. Sign up with just an email and password.
How it works
Sign Up
Create an account with email and password to receive your API key instantly.
Update Base URL
Point your existing client code to https://api.onekeyllmapi.com/v1.
Send Requests
Use the same request format as OpenAI to chat with the uncensored model.
What people build with it
Creative Writing
Generate stories and scripts without content filters blocking mature or controversial themes. Ideal for fiction where refusal rates matter.
Data Extraction
Parse large documents using the 100k context window. Get raw outputs without unnecessary stylistic refusals or safety layers.
Roleplay Apps
Build character-driven apps that stay in character. The uncensored model handles adult topics lawfully without blocking.
Research Analysis
Analyze security research or political texts without bias filters. Get direct answers to complex prompts.
Drop-In Compatibility
We provide a single, dedicated uncensored API endpoint that is fully compatible with the OpenAI chat-completions format. This means you can switch your provider without rewriting your application logic. Simply update your base_url to https://api.onekeyllmapi.com/v1 and insert your new API key. The model ID is uncensored. We support streaming via Server-Sent Events (SSE) and tool/function calling, matching the behavior developers expect from major providers.
Unlike aggregators that route requests across dozens of different vendor models, we offer one consistent, open-weight model run on our own GPU servers. This eliminates the complexity of managing multiple endpoints and ensures predictable behavior. You get direct access to the uncensored model without hidden routing layers or vendor lock-in. Our API supports text-in, text-out operations with full context window capabilities, making it a direct replacement for standard LLM integrations.
Uncensored & Lawful
Our model is tuned to answer without content refusals for lawful adult use. It does not block controversial, fictional, or security-research topics just because they are sensitive. However, we maintain a clear boundary: requests involving sexual content with minors are always blocked. This is a hard limit that applies to all requests. You get the freedom to generate mature content without the model refusing based on subjective policy interpretations common in other models.
We do not offer embeddings, image generation, audio, or video capabilities. This is a text-only API. If you need multimodal features, this is not the right tool. Our focus is on providing a reliable, uncensored text generation endpoint. We do not use your prompts for training, ensuring your data remains private. The model is not GPT, Claude, Gemini, or any other vendor's model; it is a distinct open-weight model optimized for this specific use case.
100k Context Window
Our API supports a 100,000 token context window, combining both prompt and completion tokens. This allows you to process large documents, long conversations, or complex codebases in a single request. The 8 MB request body limit ensures stable performance for these large inputs. You do not need to chunk your data manually if it fits within this window, simplifying your application architecture.
This capacity is critical for tasks requiring deep context, such as summarizing entire books or maintaining long-term state in chat applications. The model processes the full context to generate relevant, coherent responses. We do not charge extra for the context window; the price is based on token volume. This makes it cost-effective to handle large inputs compared to providers that charge premium rates for extended context.
Streaming & Tools
Our API supports streaming and tool calling
Simple Pricing
We offer transparent, pay-as-you-go pricing with no monthly fees. Input tokens cost $0.15 per 1 million tokens, and output tokens cost $0.50 per 1 million tokens. You can top up your account starting at $20 using crypto (USDT on TRC20, USDC on Base). We offer bonus credits: +5% for deposits of $50 or more, +10% for deposits of $100 or more, and +15% for deposits of $200 or more. Your paid credit never expires, so you can use it whenever you need it.
New users get $0.50 of trial credit, one per person, valid for 7 days, with no card required. This allows you to test the API immediately. Claim this credit with one click on your API key page. We do not offer free unlimited tiers or subscriptions. You pay only for what you use. This model is ideal for developers who want predictable costs without the complexity of tiered plans or hidden fees. If you need SLAs or enterprise support, this simple pricing structure may not fit your needs.
Questions and answers
Is this API compatible with the OpenAI SDK?
Yes. It uses the same /v1/chat/completions endpoint format. You only need to change the base_url and API key in your existing code. We support streaming and tool calling, matching standard OpenAI behaviors.
What is the context window size?
The API supports a 100,000 token context window for both input and output. This allows you to process large documents or long conversations in a single request, provided the request body is under 8 MB.
Do you offer image or audio generation?
No. This is a text-only API. We do not offer embeddings, image generation, audio, or video capabilities. If you need multimodal features, you will need a different provider.
How much does it cost?
Input tokens are $0.15 per 1M tokens, and output tokens are $0.50 per 1M tokens. There are no monthly fees. You can start with $0.50 in trial credit or top up with $20 or more.
Is this API for me?
This API is for developers who want a single, uncensored model without routing complexity. It is not for you if you need embeddings, image generation, or enterprise SLAs. It is also not for you if you prefer a free tier or subscription model.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Guides
Practical articles on setup, pricing and integration.
OpenAI Compatible API in n8n: Setup GuideConnect n8n to an OpenAI-compatible API: set the base URL and key, pick the model ID, build a chat workflow, use JSON mode and handle 429 errors.
LLM API Error 429: Causes and How to Fix ItAn llm api error 429 means a limit was hit. Learn the three causes here (rate_limited, concurrency, overload), how streams hold slots, and Python…
Local LLM OpenAI API: Run Local, Switch to HostedHow a local LLM OpenAI API works, what compatible really covers, and how to move the same client code to a hosted endpoint by changing three values.
LLM Observability: Myths vs Facts for DevelopersDoes LLM observability require complex infrastructure? We break down the myths and facts about tracking latency, costs, and content in your LLM API.