EN ▾
Get API Key

mugeomyeol ai API Quick Start

The mugeomyeol ai API provides an OpenAI-compatible interface, allowing you to start generating uncensored text for NSFW content creation immediately.

Base URL
https://api.mugeomyeolapi.com/v1
Model
uncensored

Set Base URL

To use the mugeomyeol ai API, change the Base URL in your client settings to https://api.mugeomyeolapi.com/v1. This URL is compatible with the official OpenAI SDK and other OpenAI-compatible clients, making it easy to adjust connection settings in existing projects. API key authentication is performed via the HTTP header Authorization: Bearer YOUR_API_KEY. Insert the API key generated for your account into this header to gain access to the endpoint. This step sets up the basic connection required for building an NSFW chatbot API or other integrations.

API Key Authentication

API keys can be generated and viewed immediately on the 'Get API key' page using your email and password. The key is uniquely linked to your account and can be refreshed at any time, invalidating the old key immediately. Including the key in the authentication header allows the server to identify the user and check token limits when making requests to the /v1/chat/completions endpoint. mugeomyeol ai does not require additional authentication steps, allowing developers to quickly test the API and accelerate the integration process.

Chat Completion Endpoint

The core feature of mugeomyeol ai is the POST /v1/chat/completions endpoint. This endpoint accepts text input and returns responses from the uncensored LLM API. The model ID is fixed to uncensored. You can use this endpoint for NSFW content generation, interactive storytelling, or other unrestricted text generation tasks. The context window supports up to 100,000 tokens in total (prompt + completion), making it suitable for long conversations or document generation. No other endpoints (embeddings, images, etc.) are provided, so it should be used for text generation only.

Streaming Response

Use streaming if you need real-time feedback during large text generation. mugeomyeol ai supports SSE (Streaming Server Events) to send responses token by token. This allows users to see parts of the text before the full response is complete, making the response speed of the NSFW chatbot API feel more natural. Streaming mode is enabled via the stream=True parameter in the OpenAI SDK. This helps reduce latency and improve resource efficiency.

Using Python SDK

Python developers can easily interact with the mugeomyeol ai API using the official OpenAI SDK. After setting the Base URL and API key, you can send requests by calling the ChatCompletion.create() method. This SDK automates streaming, token counting, and error handling, increasing development efficiency. The mugeomyeol ai API is ideal for rapidly prototyping and deploying NSFW content generation logic in Python environments.

Node.js SDK and Limits

Node.js developers can also leverage the same OpenAI-compatible interface using the openai npm package. Checking limits is important. The mugeomyeol ai API allows 300 requests per key per minute, and the request body size can be up to 8MB. A 401 error means an invalid API key, and a 429 error indicates you have exceeded the request limit. The 100,000-token context window is the sum of the prompt and generated text. Unlimited usage is available within these limits.

cURL

curl https://api.mugeomyeolapi.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."}]
  }'

Python

from openai import OpenAI

client = OpenAI(base_url="https://api.mugeomyeolapi.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)

Node.js

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.mugeomyeolapi.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);

Streaming

stream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

API specifications

A quick checklist for developers: format, limits, features, billing.

ItemValue
CompatibilityOpenAI Chat Completions schema; official openai SDKs work unchanged
EndpointsPOST /v1/chat/completions · GET /v1/models
Modeluncensored
AuthenticationAuthorization: Bearer YOUR_KEY
Base URLhttps://api.mugeomyeolapi.com/v1
Function callingSupported: tools + tool_choice, tool_calls in the reply (streamed too), tool results as role: tool messages
Structured outputJSON object mode via response_format json_object
Completion lengthup to the rest of the 100,000-token window; max_tokens optional (no separate cap)
StreamingSupported (stream: true), usage included at the end
Sampling parameterstemperature, top_p, stop, seed, presence_penalty, frequency_penalty
Max context100,000 tokens, input and output combined
Requests per minute300/min per key
HeadersX-Request-Id, X-Balance-USD, X-RateLimit-Limit-Requests, X-RateLimit-Limit-Concurrency
Max bodyup to 8 MB per request
Parallel requests8 requests at the same time per key
Paymentcrypto: USDT on TRON or USDC on Base, $20–$500, any whole sum
Price$0.15 per 1M input tokens · $0.50 per 1M output tokens
Bonus credit+5% on $50+, +10% on $100+, +15% on $200+
Billingprepaid credit, charged by real token usage; errors and refusals are free
Credit expirypaid credit never expires, no subscription
Free trial$0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Key managementone active key per account; a new key replaces the old one
Contentuncensored for adults; the only hard rule: no sexual content involving minors
Sign-insign in with Google or with e-mail + password

When a request fails

Errors come back as JSON with a stable type; failed and refused requests are not billed.

StatusTypeReason
400bad_requestinvalid JSON, empty messages, bad parameter, or a prompt longer than the window — fix and resend
401missing_key · invalid_key · key_revokedcheck the Authorization header or use your current key
402no_creditbalance is empty — top up, requests resume at once
403content_blockedsexual content involving minors — refused, not billed
404not_foundunknown endpoint
413request_too_largebody over 8 MB
429rate_limited · concurrencyover 300/min or 8 parallel — back off and retry
503upstream_busytemporary overload, retry shortly

Frequently Asked Questions

What model does the mugeomyeol ai API use?

The mugeomyeol ai API uses a self-hosted open-source uncensored LLM API model, not third-party models like GPT or Claude. The model ID is fixed to 'uncensored'.

How do I enable streaming?

When using the OpenAI SDK, set the stream=True parameter to receive streaming responses via SSE. This works identically in both Node.js and Python SDKs.

What if I lose my API key?

You can refresh your API key from the dashboard, and the old key is immediately invalidated. As long as you can access your account with email and password, you can generate a new key at any time.

API key is just by signing up

Create account, copy key, change base URL. That's all the setup you need.

Get API Key
Get API Key