CleusQwen 3.8 27B Abliterated API
The uncensored Qwen 3.8 27B: Alibaba’s model with refusals removed, over an OpenAI-compatible API. Very cheap input, image understanding and thinking you can switch off.
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": "qwen-3.8-27b-abliterated",
"messages": [
{"role": "system", "content": "You are Mara. Stay in character."},
{"role": "user", "content": "The reactor is leaking again."}
],
"stream": true
}'Qwen 3.8 27B Abliterated: the uncensored Qwen 3.8 27B
Qwen 3.8 27B is a 27-billion-parameter open-weight model from Alibaba’s Qwen team. It reads text and images, calls tools, reasons before answering and takes 262K tokens of context. The abliterated version has its refusal behaviour removed from the weights without retraining.
Input costs $0.13 per million tokens here, the lowest of the open models, so it suits work that reads much more than it writes: long prompts, retrieved documents, big system prompts, image batches.
On Cleus you call it by its own name, qwen-3.8-27b-abliterated, with nothing added in front of your system prompt.
- Retrieval and document work with long inputs and short answers
- Image description and visual question answering without content refusals
- Roleplay with large character cards and lorebooks
- Extraction and classification over unfiltered text
- Agents that call tools with thinking switched off
Call the uncensored Qwen 3.8 27B 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 qwen-3.8-27b-abliterated.
from openai import OpenAI
client = OpenAI(
base_url="https://api.cleus.ai/v1",
api_key="clsk_live_...",
)
stream = client.chat.completions.create(
model="qwen-3.8-27b-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: "qwen-3.8-27b-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": "qwen-3.8-27b-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}
}Qwen 3.8 27B Abliterated API specs
| Model id | qwen-3.8-27b-abliterated |
| Also accepted | qwen-3.8-27b-uncensored |
| Also known as | Qwen 3.8 27B Uncensored |
| Endpoint | POST https://api.cleus.ai/v1/chat/completions |
| Base model | Qwen 3.8 27B by Alibaba |
| Refusals | Removed from the weights (abliterated) |
| Context window | 262,144 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) |
| Input price | $0.13 per 1M tokens |
| Output price | $4.46 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, or "low", "medium" or "high" to set how long it thinks ("max" 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.
{
"model": "qwen-3.8-27b-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, tools, tool_choice, parallel_tool_calls, response_format, reasoning_effort. max_completion_tokens is accepted as max_tokens. Other fields are ignored.
Qwen 3.8 27B 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 | $0.13 / 1M |
| Output tokens (replies and thinking) | $4.46 / 1M |
| A chat turn: 2,000 tokens in, 500 out | $0.0025 |
| A long document: 100,000 tokens in, 2,000 out | $0.022 |
| 1,000 chat turns like the one above | $2.49 |
Failed requests are not billed. A reply you cut short is billed for what was written.
Use it in the tools you already have
Anything that accepts an OpenAI-compatible base URL can use Qwen 3.8 27B Abliterated.
| Base URL | https://api.cleus.ai/v1 |
| API key | Your Cleus key, starting clsk_live_ |
| Model | qwen-3.8-27b-abliterated |
| Works with | OpenAI SDKs (Python, Node, Go…), LangChain, LlamaIndex, LiteLLM, SillyTavern, Open WebUI, Cline, Continue, aider and other OpenAI-compatible clients |
Qwen 3.8 27B Abliterated API: questions
Is there an API for Qwen 3.8 27B Abliterated?
Yes. Cleus serves it at https://api.cleus.ai/v1/chat/completions under the model id qwen-3.8-27b-abliterated, in the OpenAI chat completions format.
What does the Qwen 3.8 27B Abliterated API cost?
$0.13 per 1M input tokens and $4.46 per 1M output tokens, from your prepaid USD balance. Thinking tokens count as output, so switch thinking off or to low for short answers.
How much context does it take?
262,144 tokens, with replies up to 65,536 tokens. For a 1M-token context use deepseek-v4.1-flash-abliterated or one of the GLM 5.3 models.
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 Qwen 3.8 27B API?
Yes. Qwen 3.8 27B Abliterated is the uncensored Qwen 3.8 27B: 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 qwen-3.8-27b-abliterated. The id qwen-3.8-27b-uncensored works too.
Is Qwen 3.8 27B Abliterated the same as Qwen 3.8 27B 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 Qwen 3.8 27B Uncensored, others as Qwen 3.8 27B 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 Qwen 3.8 27B Abliterated?
No. Requests to qwen-3.8-27b-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 qwen-3.8-27b-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.
DeepSeek V4.1 Flash Abliterated
DeepSeek V4.1 Flash with refusals removed. Thinking on or off, tool calls, images, 1M context.
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.
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 Qwen 3.8 27B API
Create a key, set the base URL, send your first request.