Uncensored LLM API with prepaid token billing

Kimicode: Uncensored LLM API for OpenAI-Compatible Clients

Kimicode provides a high-capacity, uncensored text API with prepaid billing that never expires. It is an independent alternative to major providers, running a single open-weight model tuned for lawful adult content.

Prepaid credit, never expires
Errors and refusals are free
Crypto top-ups

Get API key Read the docs

Try it in one request

curl https://api.kimicode.top/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.kimicode.top/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.kimicode.top/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

What you get

OpenAI Compatible

Use the standard /v1/chat/completions endpoint with any OpenAI SDK. Change the base_url and API key to switch from your current provider to Kimicode.

Uncensored Model

Our single model answers without content refusals for lawful adult, fictional, or controversial topics. It is not GPT, Claude, or any other vendor model.

Transparent Billing

You pay only for real token usage. Errors and refusals do not consume your credit, and prepaid balance never expires.

Crypto Payments

Top up by crypto (USDT on TRC20, USDC on Base). Amounts range from $20 to $500, with bonus credits for larger deposits.

Streaming & Tools

Supports Server-Sent Events for streaming, function calling, and JSON mode. All standard parameters like temperature and top_p are available.

Simple Access

How it works

Create Account
Sign up with Google or email to receive your API key instantly.
Top Up Credit
Deposit by crypto (USDT on TRC20, USDC on Base) to activate your prepaid balance.
Start Coding
Update your base_url and key in any OpenAI-compatible client to begin.

What people build with it

Content Generation

Generate long-form text without interruptions from content filters. Ideal for creative writing, roleplay, or adult-themed narratives.

Data Annotation

Process large volumes of text for labeling or classification without worrying about refusal rates affecting your pipeline.

Research & Analysis

Query the model for controversial or niche topics without standard corporate guardrails blocking the response.

Developer Testing

Test your application's handling of uncensored output or edge-case topics in a controlled, predictable API environment.

What is KimiCode API?

Kimicode is an independent, hosted API serving one uncensored large language model. It is not an official site or partner for DeepSeek, Together AI, or any other vendor. We run our own open-weight model tuned to answer without content refusals for lawful adult use.

The API follows the OpenAI standard. You send text, you get text back. There are no embeddings, image generation, or audio features. It is a straightforward text API designed for developers who need high-volume generation without complex subscription tiers.

Uncensored Model Capabilities

Our model is an open-weight system run on our own servers. It does not refuse lawful adult, fictional, security-research, or controversial topics. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or any other vendor's model.

The context window is 100,000 tokens total, with a maximum output of 32,000 tokens per request. We enforce a hard content limit: requests involving sexual content with minors are always refused. All other lawful adult content is permitted.

Transparent Prepaid Pricing

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. You pay only for real token usage; errors and refusals are free. There is no monthly subscription fee and no hidden costs.

Prepaid credit never expires. If you make a mistake, such as a double charge, it is fixed through Support. Credit is not refunded because it never expires, but you can use it whenever you need it. This model avoids the trap of monthly fees for unused capacity.

OpenAI Compatible Integration

Use the standard POST /v1/chat/completions endpoint. Change the base_url to https://api.kimicode.top/v1 and update your API key. All standard parameters like temperature, top_p, and stop are supported.

Streaming via SSE returns token usage in the last chunk. Function calling and JSON mode are fully supported. This is a drop-in replacement for many use cases that rely on the OpenAI API format.

Questions and answers

Is this the official DeepSeek or Together AI API?

No. Kimicode is an independent service running its own uncensored open-weight model. It is not affiliated with DeepSeek, Together AI, Groq, or any other vendor. We do not serve their models.

Does prepaid credit expire?

No. Prepaid credit never expires. You can top up when you need it and use it whenever you are ready. There is no monthly subscription fee to maintain access.

How do I top up my account?

Payments are by crypto (USDT on TRC20, USDC on Base). Minimum amount is $20, maximum is $500. We do not accept PayPal or bank transfers.

Is there a free trial?

Yes. New users get $0.50 of trial credit valid for 7 days. Claim this credit with one click on your API key page. One per person. No card is needed to start.

Is this API for me?

This is for developers who need uncensored text generation without vendor lock-in. It is NOT for you if you need image generation, embeddings, fine-tuning, or a specific vendor's model like GPT-4 or Claude.