Uncensored OpenAI-compatible API
Kimicode: an independent guide and a drop-in alternative
Drop in uncensored LLM inference without changing your existing client code. Kimicode runs a single open-weight model on our own servers, giving you full control over outputs and transparent, usage-based pricing.
- OpenAI standard endpoints
- No vendor lock-in
- Crypto top-up only
Try it in one request
curl https://api.kimicode.cc/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.cc/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.cc/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);- $0.25per 1M input tokens
- $1.00Output tokens / 1M
- 64,000token context
- $0.50trial credit
- 300requests per minute
What you get
How it works
Get Your Key
Sign up with Google or your email address to receive an API key instantly.
Add Credit
Top up your account with crypto to start using the API immediately.
Start Coding
Update your base URL and API key in your existing OpenAI SDK client.
What people build with it
Why Kimicode?
We provide a robust, open-weight API that eliminates the need for vendor-specific SDKs. By sticking to the OpenAI standard, you can swap in our endpoint with a simple configuration change. Our model is tuned to answer without content refusals, making it ideal for creative writing, roleplay, and research where standard models might block output.
The pricing is straightforward: you pay for tokens. Errors and refusals do not consume credit. This ensures you only pay for actual work done. Sign up with Google or email, and your key is ready immediately. No phone number or credit card is required to start testing.
OpenAI Compatibility
Our API mirrors the standard endpoints you already know. You can use the official OpenAI SDKs or any compatible client by updating the base URL and API key. This means your existing code works with zero modifications. We support streaming via Server-Sent Events (SSE), JSON mode, and function calling with tools.
The model accepts parameters like temperature, top_p, and stop sequences. It returns token usage in the last chunk of a stream. This compatibility allows you to build once and deploy anywhere without rewriting your integration layer.
Uncensored Model
The Kimicode API serves a single open-weight model run on our own servers. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or any other vendor's model. It is designed to answer without content refusals for lawful adult use, fiction, and security research.
There is a hard content limit: sexual content involving minors is always blocked. Everything else is allowed. This makes it a reliable choice for developers who need consistent output without fighting filters. The model handles a 64,000 token context window, allowing for deep analysis of large documents.
Simple Pricing
We charge $0.25 per million input tokens and $1.00 per million output tokens. There are no monthly fees or subscriptions. Your prepaid credit never expires, and errors are free. You can top up with USDT on TRC20 or USDC on Base, starting from $10.
Deposits of $50 or more receive a 5% bonus, and deposits of $100 or more receive a 10% bonus. We do not accept credit cards, PayPal, or bank transfers. This crypto-only model keeps overhead low and passes the savings to you.
Questions and answers
Is this the official Kimi or Llama API?
No, Kimicode is an independent service. We run our own open-weight model on our servers. It is not GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Llama, or any other vendor's model. It is designed to work with OpenAI-compatible clients.
How do I pay for the API?
We accept crypto only: USDT (TRC20) or USDC (Base). You can deposit any whole amount from $10 to $500. Deposits of $50 get a 5% bonus, and deposits of $100 get a 10% bonus. No credit cards or PayPal are accepted.
What is the context window size?
The model supports a 64,000 token context window for the combined prompt and completion. The maximum output per request is 16,000 tokens, or 2,048 tokens if you do not set the max_tokens parameter.
Is there a free trial?
Yes, every new account gets $0.50 of trial credit valid for 7 days. No card is needed to sign up or start testing. You can sign up with Google or use an email and password.
What endpoints are supported?
We support POST /v1/chat/completions and GET /v1/models. We do not offer embeddings, image, audio, video generation, or fine-tuning. Function calling, streaming, and JSON mode are all supported.
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
Get API key