Drop-in uncensored LLM API for developers
uncensored LLM API: Direct, OpenRouter Alternative for Developers
A single, uncensored OpenAI-compatible endpoint that replaces complex routing with a direct connection to our GPU servers. Change your base_url and key to start sending prompts immediately.
- One uncensored model, no routing
- $0.15/$0.50 per 1M tokens
- Drop-in OpenAI SDK compatibility
Try it in one request
curl https://api.openrouteralternativeapi.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.openrouteralternativeapi.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.openrouteralternativeapi.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);- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
What you get
Drop-in Compatibility
Works with the official OpenAI SDKs and any OpenAI-compatible client. You only need to update the base_url and API key in your configuration.
One Uncensored Model
We serve a single open-weight model tuned to answer without content refusals for lawful adult use. It is not GPT, Claude, or Gemini; it is our own tuned instance.
Transparent Pricing
Pay-as-you-go prepaid credit with no monthly fees or subscriptions. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million.
Developer-First Privacy
Create an account with just an email and password. Your prompts are not used for training, and your API key can be regenerated instantly to revoke access.
High Performance
Direct connection to our own GPU servers ensures low latency. The model supports a 100,000 token context window and streaming via SSE.
Simple Limits
Requests are capped at 300 per minute per key with an 8 MB body limit. No complex tier management or hidden throttling rules apply.
How it works
Sign Up
Register with an email and password to receive your API key instantly; no credit card is required for the trial.
Update Client
Set your base_url to https://api.openrouteralternativeapi.com/v1 and inject your new API key into your existing OpenAI-compatible client.
Send Requests
Call the /v1/chat/completions endpoint with the model id 'uncensored' to receive text responses with no content refusals.
What people build with it
Content Generation
Use the uncensored model to generate creative writing, roleplay, or fiction without hitting standard refusal gates. It handles controversial topics and adult themes for lawful use.
Data Annotation
Label datasets or generate synthetic data at scale using a direct, high-performance endpoint. The 100k context window allows processing large documents in single requests.
Security Research
Run prompt injection tests or jailbreak evaluations without worrying about the API blocking specific trigger words. The model is tuned to respond to almost any input.
Dev Testing
Test your application's logic against a reliable OpenAI-compatible API without the variability of aggregator routing. You get consistent behavior from a single model instance.
Drop-in Compatibility
Most developers already have code written for OpenAI. Our API is designed to be a direct replacement. You do not need to rewrite your logic or install new libraries. Simply point your OpenAI SDK to our base URL: https://api.openrouteralternativeapi.com/v1. Pass your API key in the header, and set the model parameter to uncensored.
This approach works with any client that supports the standard OpenAI chat-completions format. Streaming via Server-Sent Events (SSE) and tool/function calling are both supported out of the box. You get the reliability of a standard API with the flexibility of an uncensored model.
One Uncensored Model
Unlike aggregators that route between multiple vendors, we offer a single, consistent experience. Our model is an open-weight large language model running on our own GPU servers. It is specifically tuned to answer without content refusals, making it ideal for lawful adult use, creative writing, and security research.
It is not GPT, Claude, Gemini, Grok, or DeepSeek. It is a distinct model optimized for responsiveness and lack of gatekeeping. The only hard limit that always applies is the blockage of sexual content involving minors. Everything else is fair game.
Transparent Pricing
We charge only for what you use. There are no monthly subscriptions, no hidden fees, and no credits that expire. Input tokens cost $0.15 per million, and output tokens cost $0.50 per million. You can top up from $20 by crypto (USDT on TRC20, USDC on Base). Larger top-ups include bonus credit: +5% from $50, +10% from $100, +15% from $200.
New accounts start with $0.50 of trial credit valid for 7 days, requiring no card. This allows you to test the endpoint's performance and latency before committing funds. Claim this credit with one click on your API key page. You can see exactly how much each request costs in your dashboard.
Who This Is Not For
This API is not for you if you need embeddings, image generation, audio processing, or video creation. We do not offer fine-tuning or model routing between different vendors. If you require specific SLA guarantees, SOC2 certifications, or HIPAA compliance, this direct, uncensored endpoint may not meet your enterprise needs.
We also do not offer a free unlimited tier. Every request consumes tokens, and your account will stop serving when your prepaid credit is exhausted. If you need a multi-model router that automatically switches between GPT-4 and Claude based on cost or latency, look elsewhere. We provide a single, high-performance connection to one uncensored model.
Questions and answers
Is this the official OpenAI API?
No, we are an independent service. Our API is compatible with the OpenAI protocol, meaning you can use the official OpenAI SDKs by changing the base URL. However, we serve our own uncensored model, not GPT models from OpenAI.
What happens if I exceed the rate limit?
You are limited to 300 requests per minute per API key. If you exceed this, your requests will be rejected until the window resets. You can regenerate your API key at any time to get a fresh key with a new counter, which invalidates the old one.
Do you use my prompts for training?
No. We prioritize developer privacy. Your prompts are not used to train our model. You only need to provide an email and password to create an account, and your data remains yours.
Can I use this for commercial projects?
Yes, you can use the responses for commercial purposes as long as you comply with the lawful adult use policy. The model does not refuse standard commercial topics. Just ensure your use case does not involve sexual content with minors, which is always blocked.
How do I get started?
Sign up on the 'Get API key' page using just an email and password. You will receive your API key immediately and $0.50 of trial credit valid for 7 days. Claim this credit with one click on your API key page. Update your client's base URL to our endpoint and start sending requests to the 'uncensored' 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.
OpenRouter vs Direct API: Costs and TradeoffsOpenRouter vs direct API compared fairly: model choice, billing layers, fallback, privacy and code changes, plus when a router is the better pick…
How Does OpenRouter Pricing Work? Layers ExplainedHow does OpenRouter pricing work? A plain look at per-model token rates, provider differences and fees to check, compared with one flat per-token…
OpenAI-Compatible Endpoint for OpenRouter ClientsReplace an OpenRouter OpenAI-compatible endpoint with ours: base URL, model ID, auth header, streaming, tools, JSON mode, limits and 429 handling.
OpenRouter Alternative with an Open-Weight ModelNeed an OpenRouter alternative? Compare a multi-vendor router with a single open-weight model behind an OpenAI-compatible API, and see what each…
OpenRouter API Alternatives: Direct vs. AggregatorAccess an uncensored AI API key. This direct LLM API offers a simple OpenRouter alternative for developers. Start using it now.