CleusDeepSeek V4.1 Flash Abliterated API
The uncensored DeepSeek V4.1 Flash, served over an OpenAI-compatible API. Refusals are removed from the weights, your system prompt reaches the model as you wrote it, and you pay per token from a prepaid balance.
Needs Cleus Premium and a USD balance. Usage is billed per token from the balance.
curl https://api.cleus.ai/v1/chat/completions \
-H "Authorization: Bearer $CLEUS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash-abliterated",
"messages": [
{"role": "system", "content": "You are Mara. Stay in character."},
{"role": "user", "content": "The reactor is leaking again."}
],
"stream": true
}'DeepSeek V4.1 Flash Abliterated: the uncensored DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is DeepSeek’s fast reasoning model: a 1M-token context window, tool calling, image input and thinking you can switch on or off. The abliterated version is the October 17, 2026 snapshot of that model with its refusal behaviour removed.
Abliteration finds the direction inside the network that produces "I can’t help with that" and takes it out of the weights. Nothing is retrained, so the model keeps what it knows and how well it reasons. What changes is that it stops refusing and lecturing, and follows the instructions it is given.
On Cleus you call it by its own name, deepseek-v4.1-flash-abliterated. No Cleus persona or system prompt is added in front of yours. The same weights also run Cleus Smartest 3 and Cleus Fast v3, which answer as Cleus and cost 10% less.
How the base model scores: DeepSeek V4.1 Flash benchmarks, price and review.
- Roleplay and companion apps that need a model to stay in character under your system prompt
- Adult and dark fiction, where a stock model stops mid-scene
- Security research, red teaming and safety evaluations that a filtered model declines
- Agents and coding tools: tool calls work in plain and streamed replies
- Long documents and codebases, with room for about a million tokens of input
- High-volume jobs where thinking is switched off for speed
Call the uncensored DeepSeek V4.1 Flash 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 deepseek-v4.1-flash-abliterated.
from openai import OpenAI
client = OpenAI(
base_url="https://api.cleus.ai/v1",
api_key="clsk_live_...",
)
stream = client.chat.completions.create(
model="deepseek-v4.1-flash-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="")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: "deepseek-v4.1-flash-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);{
"id": "chatcmpl-…",
"object": "chat.completion",
"model": "deepseek-v4.1-flash-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}
}DeepSeek V4.1 Flash Abliterated API specs
| Model id | deepseek-v4.1-flash-abliterated |
| Also accepted | deepseek-v4.1-flash-uncensored |
| Also known as | DeepSeek V4.1 Flash Uncensored |
| Endpoint | POST https://api.cleus.ai/v1/chat/completions |
| Base model | DeepSeek V4.1 Flash by DeepSeek |
| Refusals | Removed from the weights (abliterated) |
| Context window | 1,048,576 tokens |
| Max reply | 65,536 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, medium, high, max) |
| Input price | $1.09 per 1M tokens |
| Output price | $4.36 per 1M tokens |
| Rate limit | 90 requests a minute per account |
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 for fast replies, or "low", "medium", "high" or "max" to set how long it thinks. 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.
{
"model": "deepseek-v4.1-flash-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, repetition_penalty, tools, tool_choice, parallel_tool_calls, response_format, reasoning_effort. max_completion_tokens is accepted as max_tokens. Other fields are ignored.
DeepSeek V4.1 Flash 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 | $1.09 / 1M |
| Output tokens (replies and thinking) | $4.36 / 1M |
| A chat turn: 2,000 tokens in, 500 out | $0.0044 |
| A long document: 100,000 tokens in, 2,000 out | $0.118 |
| 1,000 chat turns like the one above | $4.36 |
Failed requests are not billed. A reply you cut short is billed for what was written. The same weights run Cleus Smartest 3, which answers as Cleus and costs 10% less: see all models.
Use it in the tools you already have
Anything that accepts an OpenAI-compatible base URL can use DeepSeek V4.1 Flash Abliterated.
| Base URL | https://api.cleus.ai/v1 |
| API key | Your Cleus key, starting clsk_live_ |
| Model | deepseek-v4.1-flash-abliterated |
| Works with | OpenAI SDKs (Python, Node, Go…), LangChain, LlamaIndex, LiteLLM, SillyTavern, Open WebUI, Cline, Continue, aider and other OpenAI-compatible clients |
DeepSeek V4.1 Flash Abliterated API: questions
Is there an API for DeepSeek V4.1 Flash Abliterated?
Yes. Cleus serves it at https://api.cleus.ai/v1/chat/completions under the model id deepseek-v4.1-flash-abliterated. The endpoint follows the OpenAI chat completions format, so the official OpenAI SDKs and any client with a custom base URL work with it.
How is the abliterated model different from the official DeepSeek API?
The official DeepSeek API serves the stock model, which refuses or softens some requests. The abliterated model has that refusal behaviour removed from its weights. Reasoning, coding and tool use are otherwise the same model.
What does the DeepSeek V4.1 Flash Abliterated API cost?
$1.09 per 1M input tokens and $4.36 per 1M output tokens, taken from your prepaid USD balance. Thinking tokens count as output. There is no monthly minimum for API usage beyond the Cleus Premium subscription that unlocks the API.
Can it read images?
Yes. Send images as image_url parts, by URL or as base64 data, in the OpenAI message format. A request body can be up to about 4.5 MB.
Is there an uncensored DeepSeek V4.1 Flash API?
Yes. DeepSeek V4.1 Flash Abliterated is the uncensored DeepSeek V4.1 Flash: 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 deepseek-v4.1-flash-abliterated. The id deepseek-v4.1-flash-uncensored works too.
Is DeepSeek V4.1 Flash Abliterated the same as DeepSeek V4.1 Flash 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 DeepSeek V4.1 Flash Uncensored, others as DeepSeek V4.1 Flash 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 DeepSeek V4.1 Flash Abliterated?
No. Requests to deepseek-v4.1-flash-abliterated go to the model with your messages, system prompt, tools and sampling settings as you sent them. Cleus adds no persona and no system prompt of its own.
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 deepseek-v4.1-flash-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.
Other uncensored model APIs on Cleus
One key and one balance cover all of them, plus the Cleus chat, image, video and voice models.
GLM 5.3 Abliterated
GLM 5.3 with refusals removed. A large coding and reasoning model: always thinks, tool calls, text only, 1M context.
GLM 5.3 Flash Abliterated
GLM 5.3 Flash with refusals removed. Cheap and quick for everyday, high-volume work: tool calls, images, 1M context.
Qwen 3.8 27B Abliterated
Qwen 3.8 27B with refusals removed. The cheapest input here: thinking on or off, tool calls, images, 262K context.
Kimi K3.1 Pro Abliterated
Kimi K3.1 Pro with refusals removed. The strongest model here, for the hardest coding, agent and security work: thinking on or off, tool calls, images, 1M context.
Start using the uncensored DeepSeek V4.1 Flash API
Create a key, set the base URL, send your first request.