Drop-In Compatibility
Change your base URL and API key to use existing OpenAI SDKs. The endpoint supports standard chat completions and streaming.
Drop-in uncensored API, zero lock-in.
Drop-in uncensored API, zero lock-in.
A drop-in, open-weight LLM endpoint that replaces standard providers with one change. Get instant access to a high-context model with transparent prepaid pricing.
curl https://api.openaigatewayapi.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.openaigatewayapi.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.openaigatewayapi.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);Sign up with an email and password to receive your API key instantly.
Point your existing client to https://api.openaigatewayapi.com/v1.
Use the model ID 'uncensored' for standard chat completions.
Process large documents within the 100k context window. Extract insights without losing earlier details in long threads.
Generate stories without content filters blocking adult or controversial themes. Ideal for fictional narratives requiring specific tones.
Test model boundaries with jailbreak prompts or edge cases. Get direct responses without standard refusals for lawful testing.
Replace OpenAI in existing applications by changing the base URL. Keep your code and tool definitions intact.
This AI gateway acts as a direct substitute for major providers by supporting the standard OpenAI-compatible API format. You do not need to rewrite your application logic or change your tool definitions. Simply update your client configuration to point to https://api.openaigatewayapi.com/v1 and provide your new API key. The endpoint supports streaming via Server-Sent Events (SSE) and tool/function calling, ensuring that your existing integrations work immediately.
This approach minimizes engineering overhead. If you are already using the official OpenAI SDK or any compatible client, you can switch providers in minutes. The model ID you must send is uncensored. This is an open-weight model run on our own GPU servers, distinct from GPT, Claude, Gemini, or other commercial offerings. It provides a consistent interface for text generation without the complexity of multi-model routing.
Unlike gateways that route traffic across multiple vendor models, we offer a single, high-context endpoint. The model is open-weight and tuned to answer without content refusals for lawful adult use. This means it will not block controversial topics, security research, or fictional content that standard models might flag. The only hard limit is that requests involving sexual content with minors are always blocked.
Being open-weight means the architecture is known, but we do not claim specific benchmark scores or performance metrics compared to proprietary models. You get direct access to the output without hidden clauses. This transparency is crucial for developers who need predictable behavior without unexpected content filters interfering with their applications. It is not an enterprise-grade solution with dedicated support teams, but it is a direct line to a capable model.
Our API supports a context window of 100,000 tokens, covering both the prompt and the completion. This allows you to process large documents, long conversation histories, or complex instructions in a single request. For developers building RAG systems or analyzing lengthy reports, this capacity reduces the need for complex chunking strategies.
The limit is strict: 8 MB per request body and 300 requests per minute per key. If your use case requires embeddings, image generation, or audio processing, this API is not the right choice. We provide text in and text out. The focus is on depth of context rather than breadth of modalities. This ensures consistent performance for text-heavy tasks without the overhead of managing multiple model types.
We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly fees or subscriptions. You pay for what you use, and your prepaid credits never expire. This model eliminates the risk of paying for idle capacity or losing access to credits at the end of a billing cycle.
You can top up from $20 by crypto (USDT on TRC20, USDC on Base). Larger top-ups include bonus credits: +5% from $50, +10% from $100, and +15% from $200. New users get $0.50 of trial credit, one per person, valid for 7 days, requiring no credit card. This structure is designed for developers who want to control costs precisely. Claim this credit with one click on your API key page. Unlike enterprise plans that may include hidden fees for support or uptime guarantees, our pricing is straightforward. If you need SLA percentages or dedicated infrastructure, this independent service may not meet those specific enterprise requirements.
Yes. It supports the standard OpenAI-compatible API format. You can use the official SDK by changing the base URL to https://api.openaigatewayapi.com/v1 and updating your API key. Streaming and tool calling are supported.
The context window is 100,000 tokens, which includes both the prompt and the completion. This allows for processing large documents or long conversations in a single request.
No. Prompts sent to the API are not used for training the model. Your data remains private, and we do not claim to use it for improving our models.
The model is uncensored for lawful adult, fictional, and controversial topics. The only hard limit is that sexual content involving minors is always blocked.
Yes. You can use the output for commercial purposes. The pricing is based on token usage, and there are no additional fees for commercial use. Credits do not expire.
Create an account, copy the key, change the base URL. That is the whole setup.
Practical articles on setup, pricing and integration.
OpenAI Gateway API Explained in Plain TermsWhat people mean by an OpenAI gateway API, how it differs from a proxy or router, and where this hosted, OpenAI-compatible text endpoint fits and…
OpenAI API for Developers: Use a Compatible EndpointPoint any OpenAI SDK at a hosted, OpenAI-compatible endpoint: two settings to change, plus Python, Node and curl code for streaming, tools and…
OpenAI Gateway API Pricing: Real Cost ExamplesPay-per-token rates of $0.15 per 1M input and $0.50 per 1M output, with worked cost examples, top-up tiers and bonuses, and a free trial credit,…
LLM Gateway: setup, costs and alternativesAn in-depth analysis of the LLM gateway landscape. Compare AI gateways like LiteLLM and OpenRouter against direct uncensored API access for cost…