Drop-in LLM Gateway
Uncensored LLM API for Developers
Connect any OpenAI-compatible client to a single, purpose-built uncensored model. Change your base URL and API key; keep your code.
Drop-in uncensored chat API
Try it in one request
curl https://api.openllmgateway.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.openllmgateway.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.openllmgateway.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);https://api.openllmgateway.com/v1uncensored
OpenAI-compatible chat API
100,000 token context window
Pay-as-you-go prepaid credit
What you get
Drop-in Compatibility
Use the official OpenAI SDKs with zero code changes. Point your client to our base URL and provide your API key.
Uncensored Output
The model answers without standard content refusals for lawful adult, fictional, or research topics. Minors sexual content is blocked.
Long Context Window
Process up to 100,000 tokens of combined prompt and completion data in a single request for deep context retention.
Streaming & Tools
Supports Server-Sent Events for streaming responses and structured tool/function calling for agent workflows.
Transparent Pricing
Pay only for tokens used. $0.15 per 1M input tokens and $0.50 per 1M output tokens. No monthly fees.
Simple Limits
300 requests per minute per key with an 8 MB request body limit. Keys are instantly revocable and regeneratable.
How it works
Sign Up
Create an account with just an email and password to receive your immediate API key and trial credit.
Configure Client
Update your application's base URL to https://api.openllmgateway.com/v1 and insert your new API key.
Send Requests
Make POST requests to /v1/chat/completions using your existing OpenAI SDK integration code.
What people build with it
AI Agents
Deploy autonomous agents that require fewer content restrictions to explore broader reasoning paths. Tool calling support enables complex multi-step workflows without unexpected refusals.
Content Generation
Generate creative writing or roleplay scenarios without standard boilerplate disclaimers. The uncensored nature allows for more direct and varied output styles.
Security Research
Test model behavior against jailbreak prompts or controversial topics without immediate blocking. Useful for evaluating model robustness in diverse contexts.
Legacy Integration
Migrate existing applications built on OpenAI infrastructure to a different model provider without rewriting client logic. Ideal for quick A/B testing.
Drop-in OpenAI Compatibility
Most LLM gateways aggregate multiple providers, adding latency and complexity to your routing logic. We provide a single, dedicated endpoint for our uncensored model. This eliminates the need for custom middleware or multi-model routers. Your application uses the standard /v1/chat/completions endpoint and supports streaming via Server-Sent Events (SSE) as well as tool/function calling.
Integration requires only two changes: update your base_url to https://api.openllmgateway.com/v1 and replace your API key. All other parameters, including system prompts and message structures, remain identical to the OpenAI specification. This approach ensures that your codebase stays clean and portable.
Note: We do not offer embeddings, image generation, audio processing, or fine-tuning. If your application relies on multimodal inputs or requires model routing between different vendors, this API is not the right fit.
Uncensored Content for Lawful Use
The model is tuned to answer without standard content refusals for lawful adult content, fictional narratives, and controversial topics. This makes it ideal for applications where creative freedom is prioritized over corporate safety filters. For example, agents exploring diverse reasoning paths or writers generating mature themes can operate without unexpected blockages.
We maintain one hard content limit: sexual content involving minors is always blocked. Requests containing this specific category will be rejected. Other adult or edgy content remains accessible for lawful use. This balance allows for broad creative and analytical utility while maintaining a clear boundary on specific prohibited content types.
The model is not GPT, Claude, Gemini, Grok, or DeepSeek. It is an open-weight model run on our own GPU servers, designed specifically for this uncensored behavior.
100,000 Token Context Window
Our API supports a 100,000 token context window, encompassing both the prompt and the completion. This allows you to process large documents, maintain extensive conversation histories, or inject significant system instructions in a single request. For applications requiring deep context retention or batch processing of long texts, this capacity reduces the need for complex chunking strategies.
The request body size is limited to 8 MB, which aligns with the token capacity for most text-based inputs. Streaming responses are supported, allowing you to process tokens as they are generated rather than waiting for the full completion. This reduces perceived latency for long outputs and improves the user experience for real-time applications.
Simple Pay-As-You-Go Pricing
We charge based on actual token usage with no monthly subscriptions or hidden fees. Input tokens cost $0.15 per 1 million tokens, and output tokens cost $0.50 per 1 million tokens. You prepay for credit, and it never expires. This model ensures you only pay for what you use, making it cost-effective for both sporadic usage and high-volume production workloads.
Top-ups start at $20 by card (Visa, Mastercard, Apple Pay, Google Pay) or crypto (USDT or USDC). We offer bonus credit for larger purchases: +5% from $50, +10% from $100, +15% from $200. New accounts receive $0.50 in trial credit valid for 7 days, requiring no credit card. This low barrier to entry allows you to test the API's performance and reliability before committing to a larger balance. Claim this credit with one click on your API key page.
Guides
Practical articles on setup, pricing and integration.
LLM Gateway in Python: Calling a Backend EndpointBuild an llm gateway python service with FastAPI and httpx: auth tokens, retries, concurrency cap, and streaming passthrough to an…
LLM Gateway vs OpenRouter: Which Do You Need?LLM gateway vs OpenRouter explained: hosted routers, self-run gateways and single endpoints compared, with notes on when each one is the right choice.
What Is an LLM Gateway? Plain ExplanationAn LLM gateway is a layer between your app and model APIs. Learn what it does, when you need one, and where a hosted OpenAI-compatible endpoint…
AI Gateway Checklist: 7 Steps to Production-Ready IntegrationHosted LLM API checklist for production. Pay as you go LLM API with 100k context. Start integrating today.Questions and answers
Is this API compatible with the OpenAI SDK?
Yes. The API follows the OpenAI chat completions specification. You can use the official OpenAI SDKs by changing the base URL to https://api.openllmgateway.com/v1 and providing your API key. All standard parameters like messages, temperature, and streaming work as expected.
Does the model refuse content?
The model is uncensored and generally does not refuse lawful adult, fictional, or controversial topics. However, sexual content involving minors is always blocked. Other content restrictions are minimal compared to standard commercial models.
What is the context window size?
The context window is 100,000 tokens, covering both the input prompt and the generated output. This allows for handling large documents or long conversation histories in a single request.
How does billing work?
Billing is pay-as-you-go based on token usage. Input tokens are $0.15 per 1M, and output tokens are $0.50 per 1M. You prepay credit, which never expires. There are no monthly fees or subscriptions.
Is this a routing service for multiple models?
No. We provide a single, dedicated endpoint for our own uncensored model. We do not route between vendors like GPT-4 or Claude, nor do we offer multiple model choices. If you need multi-model routing, this gateway is not the right solution.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
