True Uncensored Inference
Our model answers without refusals for lawful adult use.
Uncensored API
So which do i use? for uncensored generation
Stop guessing which uncensored AI works for your NSFW chatbot. Get a cheap LLM API with a 100,000 token context window and pay per token billing.
- 100k token context window
- $0.15 per 1M input tokens
- OpenAI compatible endpoints
$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute
Test with one call
curl https://api.sowhichdoiuse.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "return a list of open source libraries for real time chat"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.sowhichdoiuse.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.sowhichdoiuse.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);Core capabilities
Predictable Token Billing
Pay $0.15 per 1M input tokens with no hidden fees.
OpenAI Compatible
Use the official SDKs with our simple base URL.
Crypto Payments Only
Top up with USDT or USDC and get bonus credit.
No Subscription Required
Credit never expires and errors are charged zero tokens.
Streamlined Sign-up
Get your API key instantly via Google or email.
Setup process
Create Account
Sign in with Google or email to get your key.
Add Crypto Credit
Deposit USDT or USDC to start using the API.
Send Requests
Point your client to our base URL and start generating.
Community projects
NSFW Character Chat
Build reliable roleplay apps without content filter interruptions.
Adult Content Generation
Generate unrestricted stories and images for mature audiences.
Unfiltered Research
Run experiments on controversial topics without standard refusals.
Developer Prototyping
Test uncensored models with low cost per token usage.
Who it's for: NSFW apps, not corporate dashboards
Use this uncensored LLM for apps that need raw, unfiltered text generation without corporate content filters. It powers NSFW chatbot interfaces and adult-oriented creative writing tools that require consistent, refusal-free outputs for lawful adult use. The API is ideal for developers prioritizing transparent prepaid token billing and OpenAI-compatible infrastructure. It is not for corporate dashboards requiring embeddings, image generation, or strict brand-safe moderation layers. You get direct, uncensored AI inference without subscription lock-in.
How we differ: 5 signs of a truly uncensored API
We deliver genuine uncensored generation without hidden filters. Our API charges strictly per token used, ensuring predictable costs for your NSFW chatbot projects. You receive an OpenAI-compatible endpoint with a 100k context window and no subscription lock-in. Unlike standard models, we allow lawful adult content and controversial topics without refusal. This transparent prepaid model eliminates surprise charges, giving developers reliable, unrestricted text output.
so which do i use?
Use our API when you need an uncensored LLM that answers without refusals for lawful adult content, avoiding the hidden filters of major competitors.
NSFW Chat Applications
Build unrestricted chatbots where the model generates content without blocking specific topics, ensuring consistent output for your users.
Content Generation Pipelines
Automate creative writing or roleplay scenarios where standard models might refuse edge cases, giving you predictable costs and no subscription lock-in.
Developer Testing
Verify how your app handles unfiltered responses by swapping the base_url in your existing OpenAI-compatible client and sending requests to our endpoint.
What developers actually ask: Context, tokens, and filters
What developers actually ask: Context, tokens, and filters
Our API serves a single uncensored LLM with a 100,000-token context window. We do not offer embeddings, images, or fine-tuning. You pay per token. Errors are free. No subscription locks you in. We refuse only sexual content involving minors. Everything else is allowed. Use our base URL and standard SDKs. Stream responses via SSE. Tools and JSON mode work. Credit never expires. Top up with crypto only. Start with trial credit.
Migrate from OpenAI in three steps
Switch to our uncensored API by changing three lines of code. First, update your base URL to HTTPS://api.sowhichdoiuse.com/v1. Second, replace your existing API key with the key generated on our dashboard. Third, set the model parameter to "uncensored" in your requests.
- Update
base_url. - Swap the
api_key. - Set
modeltouncensored.
Our endpoint is fully OpenAI-compatible, so streaming and JSON modes work immediately without restructuring your logic.
Worked cost examples: Token arithmetic and pricing
Our prepaid billing charges strictly per token consumed. Each million input tokens costs $0.15, while output tokens cost $0.50. For example, a request using 50,000 input and 10,000 output tokens totals $0.025 plus $0.005, resulting in $0.03 total. Errors consume no credits. This transparent structure ensures you pay exactly for what the model generates, avoiding hidden fees or subscription lock-in during peak usage.
Common questions
so which do i use? for uncensored chat completions?
Use our OpenAI-compatible endpoint. Send POST /v1/chat/completions with model id "uncensored". We serve one large language model tuned to answer without refusals for lawful adult use, avoiding hidden filters.
Does the uncensored AI model refuse content?
No, it rarely refuses lawful adult topics. A hard limit always applies: requests involving minors are refused. We do not filter controversial or security-research topics, ensuring consistent output for your application.
How much does the cheap LLM API cost per token?
Input tokens cost $0.15 per 1M; output tokens cost $0.50 per 1M. Errors and refusals are free. You pay prepaid credit by real token usage, with no monthly subscription fees or hidden charges.
What is the context window size for requests?
The context window is 100,000 tokens for prompt and completion combined. You can request up to 16,000 tokens per output. If you do not set max_tokens, the limit defaults to 2,048 tokens.
How do I top up my prepaid credit account?
We accept only crypto: USDT (TRC20) or USDC (Base). Minimum top-ups are $20. You receive a bonus credit: +5% from $50, +10% from $100, and +15% from $200 added to your balance.
Can I use the official OpenAI SDK with this API?
Yes, it is fully OpenAI-compatible. Change the base_url to HTTPS://api.sowhichdoiuse.com/v1 and provide your API key. The SDK handles streaming, JSON mode, and function calling exactly as you expect from standard clients.
Get your key via a simple form
Register, copy the token, update the base URL. That is all.
