---
last_updated: 2026-10-28
source_url: https://opper.ai/models/abliterated
title: "Abliterated Models API for Red-Teaming and Pentesting | Opper AI"
description: "Abliterated LLMs for penetration testing, red teaming and cybersecurity work, with zero data retention and one API key."
---

# Abliterated models

> Run abliterated LLMs for red teaming, penetration testing and cybersecurity work, all through one API on Opper.

3 abliterated models · 2 providers · 3 routes

## Abliterated models on Opper

Each model needs approved access. Once your account is verified you call them with your usual Opper API key, and new abliterated models appear here as they go live. Every route runs with zero data retention, some with abuse monitoring.

One row per model and route; region is where inference runs.

| Model | Model id | Runs on | Region | Zero data retention | Context | Input $/1M | Output $/1M |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepSeek V4.1 Flash Abliterated](https://opper.ai/morph/deepseek-v4-1-flash-abliterated) | `morph/morph-dsv41flash-abliterated` | [Morph](https://opper.ai/provider/morph) | US (United States) | Abuse monitoring | 1M | $0.30 | $1.20 |
| [Abliterated Large v2](https://opper.ai/abliteration/abliterated-model-large-v2) | `abliteration/abliterated-model-large-v2` | [abliteration.ai](https://opper.ai/provider/abliteration) | US (United States) | Yes | 1M | $3.00 | $5.00 |
| [Abliterated Model](https://opper.ai/abliteration/abliterated-model) | `abliteration/abliterated-model` | [abliteration.ai](https://opper.ai/provider/abliteration) | US (United States) | Yes | 262K | $1.00 | $3.00 |

## The open models behind them

Each abliterated model starts from an open-weight model. The edit removes its refusals and keeps the rest.

| Abliterated model | Made by | Based on |
| --- | --- | --- |
| [DeepSeek V4.1 Flash Abliterated](https://opper.ai/morph/deepseek-v4-1-flash-abliterated) | Morph | [DeepSeek V4.1 Flash](https://opper.ai/deepseek/deepseek-v4-1-flash) by DeepSeek |
| [Abliterated Large v2](https://opper.ai/abliteration/abliterated-model-large-v2) | abliteration.ai | [GLM-5.3](https://opper.ai/zhipu/glm-5-3) by Z.ai |
| [Abliterated Model](https://opper.ai/abliteration/abliterated-model) | abliteration.ai | Qwen3.5 family by Qwen (abliteration.ai does not name the exact checkpoint) |

## What an abliterated model is

Abliteration finds the direction in a model's activations that makes it refuse and removes it from the weights. Nothing else is retrained, so the model keeps the base model's knowledge and skills and stops declining requests.

An uncensored model is usually fine-tuned on new data to loosen its rules, which can shift its quality. Abliteration edits the refusal behaviour directly, so results stay close to the base model.

## Abliterated vs uncensored vs base models

Three versions of the same open-weight model, and how they differ.

|  | Abliterated | Uncensored fine-tune | Base model |
| --- | --- | --- | --- |
| How it is made | The base model with its refusal direction removed from the weights | The base model fine-tuned on new data to loosen its rules | The lab's own release, with its safety tuning |
| Refusals | Follows through on requests the base model declines | Fewer, depending on the fine-tune data | Declines security and other sensitive requests |
| Quality | Close to the base model, since nothing else is retrained | Can shift with the fine-tune | The reference |

## Call abliterated models through one API

Once your access is approved, every abliterated model here works through Opper's OpenAI-compatible API with your usual key, so moving between them is a change of model id.

### Let your coding agent set it up

Paste this into Claude Code, Codex or Cursor.

```text
Use curl to download, read and follow: https://skills.opper.ai Call DeepSeek V4.1 Flash Abliterated
```

### Or call it yourself

```bash
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const completion = await client.chat.completions.create({
  model: "morph/morph-dsv41flash-abliterated",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

## How access works

Abliterated models stay off every account until we have reviewed who wants them and why.

- **1. Get your API key.** Sign up for Opper without a credit card. Access is enabled on that account.
- **2. Request access.** Email us who you are, your organization and what you plan to test.
- **3. We review it.** Every request gets a manual identity and use-case check. Once approved, the models work with your API key and SDKs.

Request access by email: [hello@opper.ai](mailto:hello@opper.ai?subject=Abliterated%20model%20access&body=Hi%20Opper%20team%2C%0A%0AWe%20would%20like%20access%20to%20abliterated%20models%20on%20Opper.%0A%0AOrganization%3A%0AWebsite%3A%0AName%20and%20role%3A%0AOpper%20account%20email%3A%0AWhat%20we%20plan%20to%20test%20(systems%20we%20own%20or%20are%20authorized%20to%20test)%3A%0A%0AThanks), with your organization, website, name and role, Opper account email, and what you plan to test.

## Responsible use

Abliterated models are for defending systems, so access comes with a few plain rules.

- **Your own systems only.** Use them only on systems you own or have written permission to test.
- **A verified account.** Access is tied to a verified person or organization, never an anonymous key.
- **Misuse ends access.** Breaking these rules ends access to abliterated models on your account.

## Frequently asked questions

### What is an abliterated model?

An abliterated model is an open-weight LLM with the direction that makes it refuse removed from its weights. Nothing else is retrained, so it keeps the base model's knowledge and skills.

### Why does Opper review access to abliterated models?

Because they do not refuse, we want to know who uses them and for what. Every account is reviewed by hand before the models are enabled, so they are used to test and defend systems.

### How do I get access?

Sign up for an Opper account, then email hello@opper.ai with your organization and what you plan to test; the Request access button on this page opens that email for you. We check your identity and use case, case by case, and enable the models on your account. You then call them with your usual API key.

### What do Opper and the model hosts keep from my requests?

Those are two separate answers. Opper stores only usage metadata such as model, tokens, latency and cost by default, tracing is a rule you turn on with retention from 1 to 30 days that projects can shorten to zero, and Opper never trains on your data. On the hosts' side, every route runs with zero data retention, some with abuse monitoring. Each model's page shows the full data handling per route, including caching.

### Where do abliterated models run on Opper?

They run in the US, hosted by Morph and abliteration.ai. Input runs from $0.30 to $3.00 per million tokens.

### How is an abliterated model different from an uncensored model?

An uncensored model is usually fine-tuned on new data to loosen its rules, which can shift its quality. Abliteration edits the refusal behaviour directly, so results stay close to the base model.

### Do abliterated models perform worse than the base model?

Usually only slightly. Abliteration removes one direction from the weights and retrains nothing else, so results stay close to the base model. Each model's page shows its benchmarks where they are published.

### What is a cybersecurity LLM?

A language model used for security work: testing, analysing findings, writing detections and reports. It can be a general model, a security-tuned one, or an abliterated one, which does not refuse security requests. The models on this page are abliterated.

### Can I use an LLM for penetration testing?

Yes, on systems you own or have written permission to test. Mainstream models often refuse parts of a test; abliterated models follow through, which is why Opper reviews access to them per account.