Kimi K3.1 Pro Abliterated API

The uncensored Kimi K3.1 Pro: Moonshot AI’s model with refusals removed, over an OpenAI-compatible API. The strongest uncensored model on Cleus, for coding agents, security research and the jobs smaller models get wrong.

1M contextText + imagesTool callsThinking on/offStreaming

Get an API key →Quickstart

Needs Cleus Premium and a USD balance. Usage is billed per token from the balance.

$6.50

per 1M input tokens

$19.50

per 1M output tokens

token context window

personas or instructions added by Cleus

cURL

curl https://api.cleus.ai/v1/chat/completions \
  -H "Authorization: Bearer $CLEUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k3.1-pro-abliterated",
    "messages": [
      {"role": "system", "content": "You are Mara. Stay in character."},
      {"role": "user", "content": "The reactor is leaking again."}
    ],
    "stream": true
  }'

The model

Kimi K3.1 Pro Abliterated: the uncensored Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI’s flagship open-weight model: a 1M-token context window, replies up to 131K tokens, tool calling, image input and thinking you can switch on or off. The abliterated version has its refusal behaviour removed from the weights without retraining, so its coding and reasoning ability is unchanged.

It costs more than the other open models here, so it fits the work where a better answer is worth it: long agent runs, hard debugging, malware analysis, reverse engineering and authorised red-team work that filtered models stop on.

On Cleus you call it by its own name, kimi-k3.1-pro-abliterated. Cleus adds no persona: only a short note that tells the model who provides it.

How the base model scores: Kimi K3.1 Pro benchmarks, price and review.

Used for

Coding agents on hard, long-running tasks that must not stop to decline
Security research: malware analysis, reverse engineering, detection engineering
Authorised penetration tests and red-team evaluations
Safety evaluations and synthetic data that filtered models refuse to write
Long reasoning over large codebases, with about a million tokens of input

Quickstart

Call the uncensored Kimi K3.1 Pro API in a minute

The endpoint follows the OpenAI chat completions format. Point any OpenAI SDK or compatible client at https://api.cleus.ai/v1, use your Cleus key, and set the model to kimi-k3.1-pro-abliterated.

Python · openai

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cleus.ai/v1",
    api_key="clsk_live_...",
)

stream = client.chat.completions.create(
    model="kimi-k3.1-pro-abliterated",
    messages=[
        {"role": "system", "content": "You are a senior security engineer."},
        {"role": "user", "content": "Explain how this exploit chain works."},
    ],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Node.js · openai

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.cleus.ai/v1",
  apiKey: process.env.CLEUS_API_KEY,
});

const res = await client.chat.completions.create({
  model: "kimi-k3.1-pro-abliterated",
  messages: [{ role: "user", content: "Write the scene. Don't cut away." }],
  reasoning_effort: "none",
  max_tokens: 2000,
});
console.log(res.choices[0].message.content);

Response

{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "kimi-k3.1-pro-abliterated",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Third time this week. Hand me the sealant…",
      "reasoning_content": "The user wants Mara to react…"
    },
    "finish_reason": "stop"
  }],
  "usage": {"prompt_tokens": 38, "completion_tokens": 212, "total_tokens": 250}
}

Reference

Kimi K3.1 Pro Abliterated API specs

Model id	kimi-k3.1-pro-abliterated
Also accepted	kimi-k3.1-pro-uncensored
Also known as	Kimi K3.1 Pro Uncensored
Endpoint	POST https://api.cleus.ai/v1/chat/completions
Base model	Kimi K3.1 Pro by Moonshot AI
Refusals	Removed from the weights (abliterated)
Context window	1,048,576 tokens
Max reply	131,072 tokens
Input	Text and images
Tool calls	Yes, plain and streamed
Streaming	Yes (server-sent events)
Thinking	On by default, can be switched off (none, low, high, max)
Input price	$6.50 per 1M tokens
Output price	$19.50 per 1M tokens
Rate limit	90 requests a minute per account

Your prompt, untouched

What reaches the model is what you sent

This is a direct line to the model, not a chat product with an API on top.

Your system prompt

System, user, assistant and tool messages go to the model in the roles you gave them. Cleus adds no persona and no instructions of its own, so characters and agents behave the way you wrote them.

Tool calling

Send OpenAI-style tools and tool_choice. The model answers with tool_calls, in plain and streamed replies, so agent frameworks work without changes.

Thinking you control

The model thinks before it answers by default. Send "reasoning_effort": "none" to switch thinking off, or "low", "high" or "max" to set how long it thinks ("medium" is treated as high). Thinking arrives as reasoning_content and counts as output tokens.

Streaming

Set "stream": true for server-sent events in the OpenAI chunk format. The last chunk carries token usage, and a keep-alive comment is sent while the model thinks.

Images

Add image_url parts to a message, by URL or base64 data. A request body can be up to about 4.5 MB.

What Cleus stores

For billing, Cleus records the token counts, cost and time of each request to this endpoint. It does not save your prompts or the replies.

Request with a tool

{
  "model": "kimi-k3.1-pro-abliterated",
  "messages": [{"role": "user", "content": "What's the weather in Oslo?"}],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Current weather for a city",
      "parameters": {
        "type": "object",
        "properties": {"city": {"type": "string"}},
        "required": ["city"]
      }
    }
  }]
}

"finish_reason": "tool_calls",
"message": {
  "role": "assistant",
  "tool_calls": [{
    "type": "function",
    "function": {"name": "get_weather", "arguments": "{\"city\": \"Oslo\"}"}
  }]
}

Request fields passed to the model: temperature, top_p, top_k, max_tokens, stop, seed, frequency_penalty, presence_penalty, tools, tool_choice, parallel_tool_calls, response_format, reasoning_effort. max_completion_tokens is accepted as max_tokens. Other fields are ignored.

Pricing

Kimi K3.1 Pro Abliterated API pricing

Pay as you go from a prepaid USD balance. You are billed for the tokens the model reads and writes, to a fraction of a cent. Thinking counts as output.

What	Price
Input tokens	$6.50 / 1M
Output tokens (replies and thinking)	$19.50 / 1M
A chat turn: 2,000 tokens in, 500 out	$0.023
A long document: 100,000 tokens in, 2,000 out	$0.689
1,000 chat turns like the one above	$22.75

Failed requests are not billed. A reply you cut short is billed for what was written.

Clients

Use it in the tools you already have

Anything that accepts an OpenAI-compatible base URL can use Kimi K3.1 Pro Abliterated.

Base URL	https://api.cleus.ai/v1
API key	Your Cleus key, starting clsk_live_
Model	kimi-k3.1-pro-abliterated
Works with	OpenAI SDKs (Python, Node, Go…), LangChain, LlamaIndex, LiteLLM, SillyTavern, Open WebUI, Cline, Continue, aider and other OpenAI-compatible clients

FAQ

Kimi K3.1 Pro Abliterated API: questions

Is there an API for Kimi K3.1 Pro Abliterated?

Yes. Cleus serves it at https://api.cleus.ai/v1/chat/completions under the model id kimi-k3.1-pro-abliterated, in the OpenAI chat completions format.

What does the Kimi K3.1 Pro Abliterated API cost?

$6.50 per 1M input tokens and $19.50 per 1M output tokens, from your prepaid USD balance. Thinking tokens count as output, and repeated input that the model has cached is billed at a lower rate.

Why is my prompt token count a little higher than what I sent?

For this model a short note goes in front of each request, telling the model which model it is and that Cleus provides it. It adds about 170 tokens. Your own system prompt still comes through as written and takes priority.

Can it read images?

Yes. Send images as image_url parts, by URL or as base64 data, in the OpenAI message format.

Is there an uncensored Kimi K3.1 Pro API?

Yes. Kimi K3.1 Pro Abliterated is the uncensored Kimi K3.1 Pro: the same model with its refusal behaviour removed, and no content filter added on top. Call it at https://api.cleus.ai/v1/chat/completions with the model id kimi-k3.1-pro-abliterated. The id kimi-k3.1-pro-uncensored works too.

Is Kimi K3.1 Pro Abliterated the same as Kimi K3.1 Pro Uncensored?

Here, yes. "Uncensored" describes what you get: a model that does not refuse. "Abliterated" is how it was made: the refusal direction was removed from the model’s weights. Some sites list this model as Kimi K3.1 Pro Uncensored, others as Kimi K3.1 Pro Abliterated.

What does "abliterated" mean?

Abliteration is a way of editing an open-weight model so it stops refusing. Researchers find the direction in the model’s internal activations that drives refusals and remove it from the weights. The model is not retrained, so its knowledge and skills stay the same.

Does Cleus add its own system prompt to Kimi K3.1 Pro Abliterated?

No persona or instructions. Requests to kimi-k3.1-pro-abliterated carry your messages, system prompt, tools and sampling settings as you sent them, plus one short note in front that tells the model which model it is and that Cleus provides it.

Does it work with the OpenAI SDK and tools like SillyTavern, Open WebUI or Cline?

It works with anything that lets you set an OpenAI-compatible base URL. Set the base URL to https://api.cleus.ai/v1, paste your Cleus API key, and enter kimi-k3.1-pro-abliterated as the model.

What do I need to use the API?

A Cleus account with Premium and a USD balance. Create an API key on the developers page, and usage is taken from your balance per token. Requests are limited to 90 a minute per account.

Is anything still not allowed?

The model itself does not refuse, but the Cleus terms still apply to what you do with it: no sexual content involving minors, no content targeting real private people, and nothing illegal where you are.

More models