Simple · Uncensored

Uncensored LLM API: Direct access to an uncensored LLM endpoint

Q: What does "uncensored" mean? Does it mean there are no limits?

"Uncensored" means the model will not refuse responses based on content topics (such as adult, violence, or controversial politics). The only hard limit is that it always blocks child sexual abuse material.

Q: Can I try it for free?

Yes. New accounts receive a $0.50 free trial credit valid for 7 days, with no credit card required.

Wu Shencha API provides a single, focused uncensored large language model via a standard OpenAI-compatible interface, giving you content-unrestricted AI capabilities on a pay-as-you-go basis.

OpenAI-compatible interface
100k context window
No monthly fee, prepaid

Get API key Read docs

Try with one click

curl https://api.wushenchaapi.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.wushenchaapi.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.wushenchaapi.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);

$0.25Input token price per 1M
$1.00Output token / 1M
100,000Token context
$0.50Free trial credit
300Requests per minute

Features

Standard-compatible interface

Directly use the /v1/chat/completions endpoint, supporting streaming and function calling, seamlessly integrating with existing OpenAI SDK clients.

Single focused model

We offer only one uncensored model, ID "uncensored", requiring no routing configuration, designed specifically to remove content restrictions.

Transparent pay as you go billing

No monthly fee, no subscription. Input $0.25/1M tokens, output $1.00/1M tokens. Prepaid balance never expires.

Privacy and content boundaries

Prompts are not used for training; only an email is required for the account. Minor sexual content involving minors is always blocked, while other legal adult and controversial topics are allowed.

Low barrier to try

New accounts receive $0.50 in free trial credit, valid for 7 days. You can start invoking without binding a credit card or phone number.

High throughput limits

300 requests/minute per API key, max request body 8MB, suitable for high-frequency text generation and real-time interaction scenarios.

Usage flow

Register account
Visit the "Get API key" page, register with email and password, and the system immediately displays your API key.
Configure SDK
Point base_url to https://api.wushenchaapi.com/v1 and enter your API key.
Send request
Call the /v1/chat/completions endpoint using model ID "uncensored" to start generating text.

Application scenarios

Roleplay and creation

Get a content-unrestricted narrative experience; the model does not reject responses due to adult, violent, or controversial topics. Ideal for creative scenarios requiring free expression.

Security research analysis

Analyze model behavior on sensitive topics without filtering training data or adjusting prompts due to preset limits.

Data labeling and cleaning

Use the 100k context window to process long documents, quickly generating structured data or performing large-scale text classification at controlled costs.

Developer prototype verification

Quickly build uncensored AI application prototypes without handling complex multi-model routing logic; connect directly to a single high-performance model.

What is Wu Shencha API

Wu Shencha API is a managed service providing a single uncensored large language model. It runs via a standard OpenAI compatible interface, meaning you can directly use existing OpenAI SDKs or compatible clients. The model ID is "uncensored", running on our own GPU servers, specifically tuned to remain open to legal adult content, fictional stories, security research, and controversial topics without content rejection.

Unlike multi-model routing platforms, we do not offer embeddings, image, audio, or video generation, nor fine-tuning services. We focus on text generation, ensuring you get stable, direct responses when you need uncensored conversational capabilities. All prompt data is not used to train your model, ensuring data privacy.

OpenAI compatible interface

Wu Shencha API is fully compatible with the OpenAI /v1/chat/completions endpoint. You only need to change the base_url to https://api.wushenchaapi.com/v1 and replace the API key to start using it. It supports Server-Sent Events (SSE) streaming responses and function calling, making it suitable for most applications requiring real-time interaction or structured output.

Endpoints: POST /v1/chat/completions (supports streaming and function calling) and GET /v1/models.
Model ID: Always use "uncensored".
Limits: Does not support embeddings, image generation, audio, video, or fine-tuning.

Note: It is not an official partner of OpenAI, nor does it provide GPT or Claude models. It provides an independent, specially tuned open-weight model.

Uncensored model features

"Uncensored" means the model does not reject responses based on content type. Whether it is adult themes, political controversy, philosophical debate, or sci-fi creation, as long as it does not involve minor sexual content, the model will try to answer. This makes it ideal for roleplay, content creation, and security research.

We retain one hard limit: we always block sexual content involving minors. Aside from that, there are no other preset content filters. This means you get more raw, direct model output without repeatedly avoiding trigger words in your prompts.

Pay as you go, no hidden fees

We use a prepaid credit system with no monthly fee or subscription. Prices are $0.25/1M input tokens and $1.00/1M output tokens. Prepaid balance never expires; you only pay for the tokens you actually use. The top up threshold is as low as $10, supporting cryptocurrencies (USDT, USDC). Top up $50 or more to get a 5% bonus, and $100 or more to get a 10% bonus.

New user benefits: Register to get $0.50 free trial credit valid for 7 days, no credit card required. One-time per account. Each account is limited to one API key, which can be reset at any time to revoke the old key.

Frequently asked questions

Does Wu Shencha API support embeddings or image generation?

No. We only offer a chat completion endpoint for text generation. If you need embeddings, images, audio, or video, you will need to look for other specialized services.

Will my prompts be used to train the model?

No. We run the model on dedicated GPU servers, and your conversation data is not used to train the base model.

What does “uncensored” mean? Does it mean there are no limits?

"Uncensored" means the model does not reject responses based on content topics (such as adult, violence, or controversial politics). The only hard limit is that it always blocks minor sexual content.

Can I try it for free?

Yes. New account registration grants $0.50 in free trial credit, valid for 7 days, without requiring credit card binding.

Who is this API for?

It is for developers who need uncensored text generation, role-playing, security research, or want to avoid the complexity of multi-model routing. If you need embeddings, image generation, or high-availability SLAs, we may not be the best choice.

Fill out the form to get your key

Create an account, copy your key, and update the Base URL. That is all the configuration you need.

Get API key Read documentation