What are the API limits?

You have 300 requests per minute per key and a maximum request size of 8 MB. Each account has one API key that you can regenerate at any time. Regenerating immediately invalidates the old key. This provides security when managing your access.

Uncensored AI Model API

Uncensored AI API key for developers

Q: How does the free trial credit work?

Every new account receives $0.50 in free trial credit valid for 7 days. No credit card is required to activate. The credit is available immediately after registration and can be used for initial tests of streaming or function calling features.

Get instant access to a powerful, uncensored language model via an OpenAI-compatible interface. Zero content filters, no overhead, just pure text-in/text-out.

100k context window for long texts
Streaming and function calling support
Prepaid without subscription or minimum commitment

Get API key Read documentation

Test with one request

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

per 1M input tokens: $0.25
Output tokens / 1M: $1.00
Context window: 100,000
Free trial credit: $0.50
Requests per minute: 300

Your benefits

OpenAI compatibility

Use existing SDKs and clients by simply adjusting the base_url and API key. Integration into your existing infrastructure is trivial.

Uncensored response quality

The model does not reject adult, controversial, or creative topics. It answers directly, without unnecessary moral filters or standard refusals.

Large context window

Process up to 100,000 tokens per request. Ideal for analyzing long documents, codebases, or historical conversations in a single pass.

Transparent pricing

Pay only for what you consume. $0.25 per 1M input tokens and $1.00 per 1M output tokens. Balance never expires.

Fast setup

Get your API key immediately after registration with email and password. No credit card required for the free trial credit, ready to use instantly.

Streaming capability

Use Server-Sent Events (SSE) for real-time responses. Perfect for chat applications needing low latency and smooth typing effects.

How it works

Create account
Register with email and password on the 'Get API key' page.
Get key
Your API key is displayed immediately and can be regenerated at any time.
Start integration
Set the base_url to https://api.kiapis.com/v1 and send your first request.

What others build with it

Creative storytelling engines

Generate unrestrained, creative stories without the typical 'safety filters' that prematurely exclude certain topics. Ideal for niche genres and experimental narratives.

Code analysis with context

Load large code snippets or entire modules into the 100k context window. The model understands the full context without distortion from prior filtering.

Controversies & debates

Use the KiApi for models that address political or social topics neutrally and without bias. The model answers controversial questions directly.

Data extraction from texts

Extract structured data from long, unstructured texts. The large context length ensures that no important information is lost at the margins.

Why KiApi? Focus on unfiltered text

Most AI platforms offer more than you need and charge more for it. KiApi focuses on the essentials: a powerful, uncensored large language model delivered via an OpenAI-compatible interface. We remove the overhead of embeddings, image generation, or fine-tuning. You get a single, highly optimized model for text-in/text-out tasks. This means lower latency and easier troubleshooting, as you don't have to worry about routing logic between different models. The model was specifically trained not to arbitrarily refuse controversial, sexually explicit (for adults), or safety-related topics. This makes it the first choice for developers who want control over the output without a black box deciding what is 'appropriate'.

Seamless OpenAI integration for existing tools

One of the biggest hurdles in deploying new AI models is integrating them into existing workflows. The KiApi solves this problem through full compatibility with the OpenAI structure. You don't need to write new client libraries. Simply change the base_url to https://api.kiapis.com/v1 and use your API key. Both the official OpenAI SDK and any OpenAI-compatible clients work immediately. Support for POST /v1/chat/completions with streaming via Server-Sent Events (SSE) and tool/function calling is built in. This allows you to switch existing chatbots or text generators to an uncensored model with minimal effort.

Large context window for long documents

Many models truncate long texts or lose the thread. KiApi offers a context window of 100,000 tokens. This means you can process long documents, entire code repositories, or long conversation histories in a single request. This is crucial for tasks requiring a deep understanding of the entire context, such as summarizing, translating complex texts, or code refactoring. Since we do not offer routing between different models, performance remains predictable and consistent, regardless of how much text you input. Response times are matched to the model size and server capacity, not the complexity of a multi-model network.

Simple pricing without subscriptions

We do not sell subscriptions and have no monthly base fees. The pricing model is transparent and simple: $0.25 per 1 million input tokens and $1.00 per 1 million output tokens. You top up prepaid credit and consume it as needed. The balance never expires. For regular users there are bonuses: from $50 you receive 5% bonus credit, from $100 even 10%. This makes the KiApi more cost-efficient than many subscription models under high utilization. You know exactly what you pay and have no hidden costs for API calls or data volume. Billing is per request, which makes cost control in your applications easier.

Frequently asked questions

Is the KiApi the same as the OpenAI API?

No, the KiApi is an independent service. However, it is compatible with the OpenAI API structure. The model we provide is our own open-weight model running on our own GPU servers. It is not GPT, Claude, Gemini or another provider's model. However, you can use the same SDKs and client structures.

How does the free trial credit work?

Every new account receives $0.50 free trial credit valid for 7 days. No credit card is required for activation. The credit is available immediately after registration and can be used for initial tests of the streaming or function calling features.

Are my prompts used for training?

No. The KiApi does not use your prompts to train the model. Your data remains private. For registration you only need an email address and a password. No phone number or credit card is required for the free trial credit.

What limits apply to the API?

You have 300 requests per minute per key and a maximum request size of 8 MB. Each account has one API key that you can regenerate at any time. When regenerated, the old key becomes invalid immediately. This provides security when managing your access.

Who is the KiApi NOT for?

The KiApi is not suitable for users who need multiple different models (e.g. GPT-4o and Claude simultaneously) or multimodal capabilities such as image or audio recognition. If you need embeddings, fine-tuning or SLA guarantees for enterprise production, this is not the right place. We offer a specialized, uncensored text endpoint without additional service overhead.

Your key is just one click away

Create account, copy key, adjust base URL. That's it.

Get API key