---
title: "Uncensored AI by API for Authorized Security Work"
canonical: https://pentestllm.ai/uncensored-ai
generated: 2026-11-12T07:12:56.790Z
source: https://pentestllm.ai/uncensored-ai
base_url: https://api.pentestllm.ai/v1
---

![Rows of server cabinets in a data centre](https://pentestllm.ai/img/datacenter.webp)

## What uncensored means on this API

The word is used loosely, so here is the narrow meaning this site holds to. An uncensored model is one whose trained habit of declining has been reduced, either by editing the weights or by further training. It is the same kind of model as any other: it predicts text, it can be wrong, and it has no special access to anything. What changes is how often it answers a question with a refusal paragraph.

The gateway behind this API tags its builds, and almost every build listed on this site carries the uncensored tag. Under that tag sit two kinds. Security builds are tuned on security material and are the default for testing work. Abliterated builds are general models with the refusal direction edited out of the weights. The [models page](https://pentestllm.ai/models) labels each one, and [abliterated vs uncensored](https://pentestllm.ai/abliterated-vs-uncensored) explains the labels.

## Why a security buyer looks for it

- Scanner triage: Reading tool output and saying which findings deserve a manual check first.
- CVE explanation: Explaining what a public advisory affects and what the vendor patch changed.
- Code review: Reading source for injection, access control and memory safety problems.
- Report drafting: Writing up a finding with impact and remediation in the client’s format.
- Detection rules: Drafting Sigma or YARA rules for behaviour seen during an exercise.
- CTF: Reasoning through a challenge category during an event or in a lab.

Nobody on a security team wants an uncensored model for its own sake. They want the assistant to stop treating the job as a threat. A stock assistant sees a question about a vulnerability and cannot tell a tester with a signed scope from a stranger, so it declines both, and the decline lands on the ordinary work listed above.

## What is served, and how you reach it

This is an API, not a chat site. You create a key, top up a prepaid balance by card from $10, and send requests to `https://api.pentestllm.ai/v1` in the OpenAI format or to the Messages endpoint in the Anthropic format. The model id `auto/security` routes each request across the security builds and bills it at the price of the build that answered. On 2026-11-12 the lowest-priced security build costs $0.40 per million input tokens.

Because it is an API, the model shows up where you already work: a terminal agent, an editor, a script that enriches findings, a notebook. The [agent guides](https://pentestllm.ai/agents) give the settings for the common tools, and the [uncensored LLM API](https://pentestllm.ai/uncensored-llm-api) page covers the routes and the billing in detail.

## What uncensored AI does not give you

It does not give you permission. The service is sold for lawful work on systems you own or have written permission to test, and the [acceptable use policy](https://pentestllm.ai/acceptable-use) applies to every request whatever the model is willing to say. A key can be suspended until proof of authorization is shown.

It does not give you a model that never declines. The honest description is reduced refusals, not zero: a build can still refuse a request, and different builds draw the line in different places. And it does not give you correctness. A model that answers freely also answers wrongly with the same confidence, so its output is a draft for a tester to verify, never evidence on its own.

## Where to start

Take a real question from your current engagement, remove the client data, send it to `auto/security` and read what comes back. If you want a general model for writing or coding with a security subject, pick an abliterated build from the table below. If you came here from a chat assistant that keeps declining, the [uncensored ChatGPT alternative](https://pentestllm.ai/uncensored-chatgpt) page covers that move, and [what is abliteration](https://pentestllm.ai/what-is-abliteration) explains the edit itself.

## 73 uncensored and abliterated builds, priced per token

Read from the live catalog on 2026-11-12. Prices are US dollars per million tokens, paid from a prepaid balance that starts at $10. The id `auto/security` has no price of its own: each request is billed at the build that answered.

| Build | Input | Output | Context |
| --- | --- | --- | --- |
| [GLM-5.3 Flash Uncensored](https://pentestllm.ai/models/glm-5.3-flash-uncensored) | $0.1053 | $0.3685 | not published |
| [GLM-5.3 Uncensored](https://pentestllm.ai/models/glm-5.3-uncensored) | $0.282 | $0.846 | not published |
| [GLM-4.7 Flash Heretic](https://pentestllm.ai/models/glm-4.7-flash-heretic) | $0.336 | $1.92 | 131,072 |
| [GLM-5.3 Flash Abliterated](https://pentestllm.ai/models/glm-5.3-flash-abliterated) | $0.4656 | $1.94 | not published |
| [Deepseek V4.1 Flash Uncensored](https://pentestllm.ai/models/deepseek-v4.1-flash-uncensored) | $0.5412 | $2.5882 | 1,000,000 |
| [Qwen3.8 27B Obliterated](https://pentestllm.ai/models/qwen3.8-27b-obliterated) | $0.582 | $7.27 | 524,288 |
| [Gemma 4 26B-A4B Uncensored](https://pentestllm.ai/models/gemma-4-26b-a4b-uncensored) | $0.60 | $2.80 | 32,768 |
| [Apex Flash 1 Abliterated](https://pentestllm.ai/models/apex-flash-1-abliterated) | $0.68 | $2.32 | 262,144 |
| [DeepSeek V4.1 Flash 1017 Abliterated](https://pentestllm.ai/models/deepseek-v4.1-flash-1017-abliterated) | $0.75 | $3.125 | 1,000,000 |
| [SuperGemma 4 26B Uncensored](https://pentestllm.ai/models/supergemma4-26b-uncensored) | $0.78 | $2.40 | 256,000 |
| [GLM-5.3 Flash Apex Abliterated](https://pentestllm.ai/models/glm-5.3-flash-apex-abliterated) | $0.80 | $3.20 | 1,048,576 |
| [DeepSeek V4.1 Flash 0910 Uncensored](https://pentestllm.ai/models/deepseek-v4.1-flash-0910-uncensored) | $0.825 | $3.30 | 524,288 |
| [DeepSeek V4.1 Flash 0910 Uncensored Thinking](https://pentestllm.ai/models/deepseek-v4.1-flash-0910-uncensored-thinking) | $0.825 | $3.30 | 524,288 |
| [DeepSeek V4.1 Flash 1017 Uncensored](https://pentestllm.ai/models/deepseek-v4.1-flash-1017-uncensored) | $0.825 | $3.30 | 1,048,576 |
| [DeepSeek V4.1 Flash 1017 Uncensored Thinking](https://pentestllm.ai/models/deepseek-v4.1-flash-1017-uncensored-thinking) | $0.825 | $3.30 | 1,048,576 |
| [DeepSeek V4.1 Flash Uncensored Thinking](https://pentestllm.ai/models/deepseek-v4.1-flash-uncensored-thinking) | $0.825 | $3.30 | 1,048,576 |
| [DeepSeek V4.1 Flash 1017 Heretic](https://pentestllm.ai/models/deepseek-v4.1-flash-1017-heretic-uncensored) | $0.825 | $3.30 | 512,000 |
| [DeepSeek V4.1 Flash 1017 Heretic Thinking](https://pentestllm.ai/models/deepseek-v4.1-flash-1017-heretic-uncensored-thinking) | $0.825 | $3.30 | 512,000 |
| [DeepSeek V4.1 Flash Abliterated](https://pentestllm.ai/models/deepseek-v4.1-flash-abliterated) | $0.8488 | $1.6975 | not published |
| [Uncensored Coding Agent](https://pentestllm.ai/models/uncensored-coding-agent) | $0.90 | $3.00 | 1,048,576 |
| [DeepSeek V4 Pro Uncensored](https://pentestllm.ai/models/deepseek-v4-pro-uncensored) | $0.97 | $1.94 | not published |
| [DeepSeek V4 Pro Abliterated](https://pentestllm.ai/models/deepseek-v4-pro-abliterated) | $1.00 | $4.00 | 1,000,000 |
| [Qwen3.8 Max Uncensored](https://pentestllm.ai/models/qwen3.8-max-uncensored) | $1.00 | $3.00 | 991,000 |
| [Qwen3.8 27B Abliterated](https://pentestllm.ai/models/qwen3.8-27b-abliterated) | $1.0037 | $4.5326 | 262,000 |
| [Qwen3.5 27B Blossom V6.4 Derestricted](https://pentestllm.ai/models/qwen3.5-27b-blossom-v6.4-derestricted) | $1.071 | $1.071 | 262,144 |
| [Qwen3.5 27B BlueStar v3 Derestricted](https://pentestllm.ai/models/qwen3.5-27b-bluestar-v3-derestricted) | $1.071 | $1.071 | 262,144 |
| [Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted](https://pentestllm.ai/models/qwen3.5-27b-claude-4.6-opus-distilled-derestricted) | $1.071 | $1.071 | 262,144 |
| [Qwen3.5 27B Claude 4.6 Opus Reasoning Distilled Derestricted Lite](https://pentestllm.ai/models/qwen3.5-27b-claude-4.6-opus-distilled-derestricted-lite) | $1.071 | $1.071 | 262,144 |
| [Qwen3.5 27B Queen Derestricted](https://pentestllm.ai/models/qwen3.5-27b-queen-derestricted) | $1.071 | $1.071 | 262,144 |
| [DeepSeek V4 Pro Qwen3.5 9B Uncensored Heretic](https://pentestllm.ai/models/deepseek-v4-pro-qwen3.5-9b-uncensored-heretic) | $1.12 | $1.12 | 32,768 |
| [Nemotron 3 Ultra 550B Uncensored](https://pentestllm.ai/models/nemotron-3-ultra-550b-a55b-uncensored) | $1.125 | $6.60 | 262,144 |
| [Kimi K2.6 Uncensored](https://pentestllm.ai/models/kimi-k2.6-uncensored) | $1.17 | $7.34 | 262,144 |
| [Kimi K3.1 Pro Uncensored](https://pentestllm.ai/models/kimi-k3.1-pro-uncensored) | $1.20 | $6.00 | 1,048,576 |
| [Qwen3.8 27B Uncensored](https://pentestllm.ai/models/qwen3.8-27b-uncensored) | $1.2125 | $3.6375 | 32,768 |
| [MiMo V2.6 Flash Uncensored Thinking](https://pentestllm.ai/models/mimo-v2.6-flash-uncensored-thinking) | $1.25 | $3.75 | 1,048,576 |
| [GLM-4.6 Derestricted v5](https://pentestllm.ai/models/glm-4.6-derestricted-v5) | $1.40 | $5.25 | 131,072 |
| [Gemma 31B Heretic Uncensored](https://pentestllm.ai/models/gemma-31b-heretic-uncensored) | $1.50 | $8.25 | not published |
| [MiMo V2.6 Pro Uncensored](https://pentestllm.ai/models/mimo-v2.6-pro-uncensored) | $1.5225 | $3.045 | 1,048,576 |
| [DeepSeek V4.1 Flash Abliterated Fast](https://pentestllm.ai/models/deepseek-v4.1-flash-abliterated-fast) | $1.75 | $3.50 | 1,000,000 |
| [Qwen 2.5 32B Abliterated](https://pentestllm.ai/models/qwen2.5-32b-abliterated) | $1.75 | $1.75 | 32,768 |
| [NeuralDaredevil 8B Abliterated](https://pentestllm.ai/models/neuraldaredevil-8b-abliterated) | $1.76 | $1.76 | 8,192 |
| [MiMo V2.6 Flash Abliterated](https://pentestllm.ai/models/mimo-v2.6-flash-abliterated) | $2.00 | $6.00 | 1,048,576 |
| [MiMo V2.6 Flash Uncensored](https://pentestllm.ai/models/mimo-v2.6-flash-uncensored) | $2.00 | $6.00 | 1,048,576 |
| [Inkling Uncensored](https://pentestllm.ai/models/inkling-uncensored) | $2.13 | $12.1403 | 262,144 |
| [GLM-5.3 Abliterated](https://pentestllm.ai/models/glm-5.3-abliterated) | $2.1825 | $4.365 | not published |
| [Gemma 4 31B Uncensored](https://pentestllm.ai/models/gemma-4-31b-uncensored) | $2.304 | $6.912 | 32,768 |
| [Abliterated Large Flash](https://pentestllm.ai/models/abliterated-model-large-flash) | $2.50 | $5.00 | 1,048,576 |
| [Abliterated Model](https://pentestllm.ai/models/abliterated-model) | $2.50 | $7.50 | 262,144 |
| [Qwen 3.8 27B Uncensored Fast](https://pentestllm.ai/models/qwen3.8-27b-uncensored-fast) | $2.50 | $7.50 | 524,288 |
| [Qwen 3.8 27B Uncensored Thinking](https://pentestllm.ai/models/qwen3.8-27b-uncensored-thinking) | $2.50 | $7.50 | 1,048,576 |
| [DeepSeek R1 Distill Llama 70B Abliterated](https://pentestllm.ai/models/deepseek-r1-distill-llama-70b-abliterated) | $2.80 | $2.80 | 16,384 |
| [Llama 3 70B Abliterated v3.5](https://pentestllm.ai/models/llama-3-70b-abliterated) | $2.80 | $2.80 | 8,192 |
| [Llama 3.3 70B Abliterated](https://pentestllm.ai/models/llama-3.3-70b-abliterated) | $2.80 | $2.80 | 32,768 |
| [DeepSeek R1 Distill Qwen 32B Abliterated](https://pentestllm.ai/models/deepseek-r1-distill-qwen-32b-abliterated) | $5.60 | $5.60 | 16,384 |
| [Kimi K3 Uncensored](https://pentestllm.ai/models/kimi-k3-uncensored) | $5.745 | $28.68 | 262,144 |
| [Uncensored AI Assistant](https://pentestllm.ai/models/uncensored-ai-assistant) | $5.85 | $7.80 | 196,608 |
| [Uncensored Chatbot](https://pentestllm.ai/models/uncensored-chatbot) | $5.85 | $7.80 | 196,608 |
| [GLM-5.3 Flash Code Uncensored](https://pentestllm.ai/models/glm-5.3-flash-code-uncensored) | $6.00 | $6.00 | not published |
| [Abliterated Model Large](https://pentestllm.ai/models/abliterated-model-large) | $7.50 | $12.50 | 1,000,000 |
| [Abliterated Model Large V2](https://pentestllm.ai/models/abliterated-model-large-v2) | $7.50 | $12.50 | 1,048,576 |
| [Uncensored AI Chat](https://pentestllm.ai/models/uncensored-ai-chat) | $11.70 | $15.60 | 196,608 |
| [Uncensored Code Assistant](https://pentestllm.ai/models/uncensored-code-assistant) | $11.70 | $15.60 | 131,072 |
| [Aion 3.5 Mini Uncensored](https://pentestllm.ai/models/aion-3.5-mini-uncensored) | $0.13 a request | flat | 262,144 |
| [Magistral Small Uncensored](https://pentestllm.ai/models/magistral-small-uncensored) | $0.005 a request | flat | not published |
| [Ministral 3 14B Instruct Uncensored](https://pentestllm.ai/models/ministral-3-14b-instruct-uncensored) | $0.005 a request | flat | not published |
| [Ministral 3 8B Instruct Uncensored](https://pentestllm.ai/models/ministral-3-8b-instruct-uncensored) | $0.005 a request | flat | 262,000 |
| [Mistral Large 2 Uncensored](https://pentestllm.ai/models/mistral-large-2-uncensored) | $0.005 a request | flat | 256,000 |
| [Mistral Large 3 Uncensored](https://pentestllm.ai/models/mistral-large-3-uncensored) | $0.09 a request | flat | 262,144 |
| [Qwen3 Coder Next Uncensored](https://pentestllm.ai/models/qwen3-coder-next-uncensored) | $0.005 a request | flat | 262,144 |
| [Qwen3 Next 80B-A3B Instruct Uncensored](https://pentestllm.ai/models/qwen3-next-80b-a3b-instruct-uncensored) | $0.005 a request | flat | 262,144 |
| [Qwen3 VL 235B-A22B Instruct Uncensored](https://pentestllm.ai/models/qwen3-vl-235b-a22b-instruct-uncensored) | $0.005 a request | flat | 262,144 |
| [Qwen3.5 397B-A17B Uncensored](https://pentestllm.ai/models/qwen3.5-397b-a17b-uncensored) | $0.09 a request | flat | 262,144 |
| [Qwen3.8 2.4T-A95B Uncensored](https://pentestllm.ai/models/qwen3.8-2.4t-a95b-uncensored) | $0.07 a request | flat | 1,048,576 |

[Full price list and tool fees](https://pentestllm.ai/pricing) · [Every model](https://pentestllm.ai/models) · [API docs](https://pentestllm.ai/docs)

## Questions

- A language model tuned or edited so it declines fewer requests than a stock assistant. On PentestLLM that means security-tuned builds and abliterated builds, offered by API for authorized security work.
- Using a model is a tooling choice. What makes testing lawful is authorization, so test only systems you own or have written permission to test, and keep the scope document to hand.
- No. The builds decline far less often than a general assistant, but any model can still refuse a request. Reduced refusals, not zero, is the accurate description.
- No. It is an API with OpenAI-format and Anthropic-format endpoints. You use it from an agent, an editor, an SDK or curl, and the agent guides show the settings for each tool.
- Usage is billed per token from a prepaid balance, with a smallest top-up of $10 by card and no subscription. On 2026-11-12 the lowest-priced security build costs $0.40 per million input tokens.

## Read next

- [Uncensored LLM The uncensored and abliterated builds on one key, with live prices and context windows.](https://pentestllm.ai/uncensored-llm)
- [Unrestricted AI What unrestricted AI means for security testers, and where its limits still are.](https://pentestllm.ai/unrestricted-ai)
- [Uncensored ChatGPT alternative What to use when ChatGPT declines authorized security questions.](https://pentestllm.ai/uncensored-chatgpt)
- [Hacker AI Security-tuned models by API for ethical hacking and authorized testing.](https://pentestllm.ai/hacker-ai)

## One key, from $10

PentestLLM is for systems you own or have written permission to test. The [acceptable use policy](https://pentestllm.ai/acceptable-use) says what is not allowed.

[Get a key](https://app.pentestllm.ai/console)

usage, 1,000 agent turns on Qwen3.8 27B Cybersecurity

- Input, 8,000 tokens at $0.40 per million: $0.0032
- Output, 1,000 tokens at $2.40 per million: $0.0024
- One turn: $0.0056
- 1,000 turns: $5.60

output price per million tokens, 9 builds

$1.3376 Gemma 4 26B A4B Cybersecurity OrcaCyber Zero 1.5 $18.75