Standard Interface
Use existing OpenAI SDKs by simply changing the base URL and API key.
Developer-First API
Uncensored model API for Developers
Get a single uncensored model via an OpenAI compatible API with a 100,000 token context window, transparent crypto pricing, and zero soft refusals for lawful adult content.
- 100,000 token context window
- $0.15 per 1M input tokens
- OpenAI compatible interface
Test with one call
curl https://api.modeluncensored.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Return the current system time in ISO format"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.modeluncensored.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.modeluncensored.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);- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
Features
High Capacity
Supports up to 100,000 tokens for complex context handling without extra complexity.
Crypto Payments
Top up with USDT or USDC and receive bonus credit on larger deposits.
No Subscriptions
Pay only for real token usage with no monthly fees or hidden costs.
Streaming Support
Access streaming via SSE with token usage details included in the final chunk.
Tool Ready
Enable function calling and JSON mode for precise programmatic integration into your app.
Setup process
Create Account
Sign up with Google or email to get your API key instantly.
Top Up Credit
Add crypto funds to your account with no card required for the trial.
Start Integrating
Point your client to our base URL and begin sending requests immediately.
Who Builds With It (And Who Should Skip)
Developers need this uncensored model API when mainstream providers refuse lawful adult or controversial content. It fits bots, story engines, and creative tools requiring unrestricted text generation without proxy complexity. Skip it if you need embeddings, image, or audio outputs. You also should skip if you require multiple model choices or fine-tuning capabilities. This API serves a single, large-context model via a standard interface, delivering consistent results for text-only applications that demand high tolerance for diverse topics.
Integrate an uncensored model Into Your Stack
Connect your application to our API by updating the base URL to HTTPS://api.modeluncensored.com/v1 and sending requests with the model ID "uncensored".
OpenAI-Compatible SDKs
Use the standard base_url parameter to route traffic through our proxy without rewriting your client logic.
Streaming Support
Receive real-time token updates via Server-Sent Events for low-latency user experiences.
JSON Mode
Enforce structured outputs with response_format for reliable data parsing in automated workflows.
Function Calling
Expose tools to the model using standard OpenAI-style function definitions.
Developers Ask: Common Unfiltered LLM Questions
Our model accepts lawful adult content without soft refusals, making it ideal for creative writing or roleplay bots. You can integrate it using the standard OpenAI-compatible endpoint at https://api.modeluncensored.com/v1 with a 100,000 token context window. Pricing is transparent: $0.15 per million input tokens and $0.50 per million output tokens. We support streaming, JSON mode, and function calling. Top-ups use crypto only, with bonus credit for larger amounts.
Migrate From Another Provider In Three Steps
Switch your integration in minutes by updating your base URL and API key. First, generate your unique key via the dashboard. Second, point your client to HTTPS://api.modeluncensored.com/v1. Third, set the model ID to "uncensored." The interface remains fully compatible, so your existing code works immediately. No retraining or complex routing is required. Start testing with the free trial credit today.
Why Our API Beats Typical Alternatives
Our API eliminates proxy complexity by serving a single, direct uncensored model via a standard OpenAI-compatible interface. This approach ensures transparent per-token pricing with crypto top-ups and immediate API keys without hidden restrictions.
| Feature | Typical Alternatives | Our API |
|---|---|---|
| Model Routing | Complex proxy routers | Single direct model |
| Pricing | Hidden fees | Transparent per-token |
| Censorship | Soft refusals | Unrestricted adult content |
From Signup To First Token: How It Works
Start by creating a free account using either Google or an email address with a password.
- Verify your identity and immediately receive your unique API key on the dashboard.
- Top up your prepaid credit using USDT or USDC, which instantly activates your billing.
- Configure your SDK with the provided base URL and key to begin sending requests.
- Send your first prompt to the uncensored model and receive a direct response.
You are ready to build without any hidden fees.
FAQ
What is an uncensored model and how does it differ from standard LLMs?
An uncensored model is an LLM designed to answer without content refusals for lawful adult use. Unlike standard models, it does not block controversial topics. Our endpoint serves one open-weight model tuned for unrestricted text generation via OpenAI-compatible interfaces.
Is this API compatible with the official OpenAI SDKs?
Yes, it is fully compatible with standard OpenAI SDKs. You simply change the base URL to HTTPS://api.modeluncensored.com/v1 and update your API key. The interface supports POST /v1/chat/completions and GET /v1/models with identical request structures.
What is the context window size for the uncensored LLM API?
The context window supports 100,000 tokens for prompt and completion combined. You can request up to 16,000 output tokens per request. If you do not specify max_tokens, the system defaults to a 2,048 token output limit automatically.
How much does the cheap LLM API cost per token?
Input tokens cost $0.15 per 1 million tokens. Output tokens cost $0.50 per 1 million tokens. Prepaid credit covers usage, and errors are free. No monthly fees apply, and your prepaid credit never expires until you use it.
Can I use the uncensored AI API for function calling?
Yes, the API supports function calling with tools and tool_choice parameters. You can also enable JSON mode via response_format json_object. Streaming via SSE is available, with token usage details provided in the final response chunk.
What payment methods are accepted for topping up credit?
We accept crypto only: USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500. You receive bonus credit of +5% from $50, +10% from $100, and +15% from $200 added to your account balance.
Get your API key
Sign up, copy your key, update the base URL. Done.
Create key