Uncensored LLM API
Unfiltered Chat API for Developers
Get a dedicated uncensored LLM for unfiltered chat with a 100k context window, prepaid crypto billing, and zero monthly fees.
- 100k context window
- $0.15 per 1M input tokens
- OpenAI compatible endpoints
curl https://api.chatunfiltered.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Check server status"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.chatunfiltered.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.chatunfiltered.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
Capabilities
OpenAI Compatible
Use standard SDKs with POST /v1/chat/completions and GET /v1/models.
Prepaid Crypto Billing
Pay only for tokens used via USDT or USDC with no subscriptions.
Unlimited Context
Process up to 100,000 tokens per request for long conversations.
Streaming Support
Receive real-time token streams via SSE with accurate usage tracking.
Function Calling
Enable tools, tool_choice, and JSON mode for structured data extraction.
Instant Setup
Get your API key immediately via Google or email in seconds.
Integration steps
Create Account
Sign up with Google or email to receive your API key instantly.
Top Up Credit
Add crypto funds starting at $20 to activate your prepaid balance.
Make Requests
Send prompts to our base URL and receive text completions immediately.
Integration examples
Roleplay Applications
Run immersive character interactions without content filters blocking creative narratives.
Bug Report Processing
Allow users to submit raw, unfiltered feedback directly to your logs.
Data Extraction
Extract structured JSON data from diverse text sources with high accuracy.
Research Analysis
Analyze large documents within the 100k window for comprehensive insights.
Stop Paying for Unused Capacity: Why Prepaid Beats Subscriptions
Prepaid billing eliminates wasted spend on idle infrastructure. Unlike subscription models that charge for reserved capacity regardless of usage, our API charges only for tokens actually processed. Errors and refusals remain free, ensuring you never pay for failed requests. This approach aligns costs directly with value delivered, allowing developers to scale efficiently without monthly overhead or complex routing fees.
The 5-Step Checklist to Verify True Uncensorship and Reliability
Verify your provider with this checklist before committing credits. First, confirm dedicated hardware runs a single uncensored model without hidden routing layers. Second, test the /v1/chat/completions endpoint for unrestricted responses on controversial topics. Third, check that prepaid token billing matches actual usage, not arbitrary limits. Fourth, ensure streaming via SSE works reliably. Finally, verify crypto-only top-ups with no subscription traps.
Unfiltered Chat Use Cases: From Roleplay to Raw Data Extraction
Our uncensored LLM handles diverse tasks without content filters blocking lawful adult, fictional, or security-research topics. It serves as a robust engine for applications requiring unrestricted dialogue or raw data extraction.
Immersive Roleplay
Generate consistent, character-driven responses without standard refusals interrupting the narrative flow.
Raw Data Extraction
Pull structured text from complex prompts while maintaining context across long conversations.
Security Research
Analyze model behavior on controversial topics without artificial guardrails limiting your scope.
Content Generation
Create adult-themed fiction or creative writing without unnecessary moderation layers.
Proxy vs. Dedicated Model: 6 Signs You Are Overpaying for Routing
A proxy routes requests through multiple models, adding latency and masking the actual model behavior. Our API serves a single, dedicated uncensored model directly, ensuring consistent responses without hidden hops. Proxies often charge for idle capacity or failed retries, whereas our prepaid credit charges only for real token usage. This direct path eliminates routing fees and provides transparent, predictable costs for every request.
| Feature | Proxy Services | Our Dedicated API |
|---|---|---|
| Routing | Multi-model | Single dedicated model |
| Pricing | Subscription/Overhead | Prepaid per token |
From Signup to First Token: The 3-Step Integration Path
- Create your account via Google or email; the API key appears instantly with no phone number required.
- Load prepaid credit using USDT (TRC20) or USDC (Base) with no card needed.
- Configure your client to point to HTTPS://api.chatunfiltered.com/v1, send your key, and invoke POST /v1/chat/completions with model "uncensored" for immediate, unfiltered responses.
Exact Token Math: How $20 in USDC Buys You Real Compute
Your prepaid credit covers only actual usage. Errors cost nothing. This $20 USDC purchase nets 23 USD after the 15% bonus. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. A 5,000-token prompt with 2,000 tokens of response consumes 0.0007 million input and 0.002 million output. The total bill is roughly $1.25. Your balance remains robust for thousands of requests.
Frequently asked questions
What is unfiltered chat and how does it differ from standard models?
Unfiltered chat refers to our dedicated uncensored LLM that answers without refusals for lawful adult content. It is a single model, not a proxy. Unlike multi-model aggregators, we do not route requests or add latency layers.
Which payment methods do you accept?
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
What is the context window size?
The context window is 100,000 tokens, combining both prompt and completion. There is no separate output cap: a response can use all the room left in the window. If you do not set max_tokens, the response can run to the end of the window.
Are errors free when using the prepaid API?
Yes. Errors and refusals do not consume your prepaid credit. You are charged only for successful token usage. This ensures you pay strictly for the compute that generates output, not for network failures.
Is the model trained on my data?
No. Your prompts are not used for training. We maintain strict privacy; an account needs only an email address. Your data remains yours, and we do not use it to improve other models.
How many concurrent requests can I make?
You can make up to 8 requests simultaneously per API key. The rate limit is 300 requests per minute. This ensures consistent performance for your application without the need for complex concurrency management.
Generate your API key
Register, copy your key, and update your base URL. That is the entire setup process.
