New: 140+ uncensored models just added — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, Qwen and more. They are new and still being perfected.Problems? Contact support on Telegram @artificialthruNew: 140+ uncensored models just added — Claude, GPT, Gemini, Grok, DeepSeek, Kimi, Qwen and more. They are new and still being perfected.Problems? Contact support on Telegram @artificialthru

Run Uncensored gpt-oss-120b without a GPU.

House build on PentestLLM as gpt-oss-120b-uncensored.

Uncensored gpt-oss-120b is an PentestLLM house build. It costs $0.146 per million input tokens and $0.728 per million output tokens, prepaid, with a 131,072-token context window. Call it at https://api.pentestllm.ai/v1/chat/completions with model "gpt-oss-120b-uncensored" and an PentestLLM key, from any OpenAI SDK or client that takes a base URL.

Get a key

Price and first request

Price per million tokens

Input
$0.146
Cached input
$0.146 (input rate)
Output
$0.728
Daily check
Steady since Oct 21
As of
2026-11-20

First request

curl
1curl https://api.pentestllm.ai/v1/chat/completions \
2 -H "Authorization: Bearer sk-ptl-live-…" \
3 -H "Content-Type: application/json" \
4 -d '{"model": "gpt-oss-120b-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'

Base URL https://api.pentestllm.ai/v1. The key comes from the console; prices settle per token.

Uncensored gpt-oss-120b specs

Kind
House build
Context window
131,072 tokens
Tool calling
Not listed in the catalog
Max output
131,072 tokens
Input
text
Wire formats
openai

Get a key

  1. Create a key in the console. Credit is prepaid from $10, with no subscription.
  2. Set OPENAI_BASE_URL to https://api.pentestllm.ai/v1 and send your sk-ptl- key as the bearer token.
  3. Send gpt-oss-120b-uncensored as the model. The same key calls every model on PentestLLM.

Uncensored gpt-oss-120b settings for OpenCode and Cline

Provider
OpenAI-compatible
Base URL
https://api.pentestllm.ai/v1
Model
gpt-oss-120b-uncensored
Context window
131,072 tokens
Max output
131,072 tokens
Key prefix
sk-ptl-

What Uncensored gpt-oss-120b is

Base model
Base parameters
117B total, 5.1B active
License of the base, read 2026-10-26
Apache-2.0
Kind
the model served without a content filter
Context window here
131,072 tokens
Max output
131,072 tokens
Input
text

From openai/gpt-oss-120b on Hugging Face (read 2026-10-26) and the live catalog.

From the SDK

openai.py
1from openai import OpenAI
2
3client = OpenAI(base_url="https://api.pentestllm.ai/v1", api_key="sk-ptl-live-…")
4
5completion = client.chat.completions.create(
6 model="gpt-oss-120b-uncensored",
7 messages=[{"role": "user", "content": "Hello"}],
8)
9print(completion.choices[0].message.content)
openai.ts
1import OpenAI from 'openai';
2
3const client = new OpenAI({ baseURL: 'https://api.pentestllm.ai/v1', apiKey: 'sk-ptl-live-…' });
4
5const completion = await client.chat.completions.create({
6 model: 'gpt-oss-120b-uncensored',
7 messages: [{ role: 'user', content: 'Hello' }],
8});
9console.log(completion.choices[0].message.content);

Guides: Cursor, Claude Code, SDKs.

What Uncensored gpt-oss-120b answers

Uncensored gpt-oss-120b is an uncensored build: it answers without the safety refusals of the stock model.

Every request is routed to the build’s live route and settled to the token at the prices above. The daily real-model check sends a fixed prompt to every model and records whether the answer still matches; this model’s verdict today is “Steady since Oct 21”.

Use it from the OpenAI SDK, or from a coding or pentest agent. Keys and top-ups live in the console: top up by card, WeChat Pay or Alipay.

Also try

More house builds

Compare

What Uncensored gpt-oss-120b costs, worked

A chat turn of 2,000 input and 500 output tokens at $0.146 input and $0.728 output per million tokens is $0.0007; 1,000 turns are $0.66. A long chat session of 100 replies of 300 tokens costs $0.0802 at 4,000 tokens of context and $0.2554 at 16,000: every message resends the context, so size it to what the chat needs. All from prepaid credit, no subscription.

House build buildsContextIn / out per 1M1,000 chat turns
Uncensored GLM 5.3 FlashX—$0.045 / $0.15$0.17
Uncensored GPT-6 Luna—$0.0625 / $0.20$0.23
Uncensored DeepSeek V4 Flash 0731262K$0.084 / $0.12$0.23
Uncensored GPT-5.6 Luna—$0.06 / $0.36$0.30
Uncensored Claude Haiku 5 5—$0.0735 / $0.40$0.35
Uncensored GPT-4.1 Nano—$0.10 / $0.40$0.40
Uncensored Qwen3.8 Flash—$0.1152 / $0.361$0.41
Uncensored Agnes 3.0 Flash—$0.12 / $0.36$0.42
Uncensored Qwen2.5 7B Instruct—$0.20 / $0.20$0.50
Uncensored GPT-4o mini—$0.15 / $0.60$0.60
Uncensored Doubao Seed 2.0 Mini—$0.096 / $0.896$0.64
Uncensored gpt-oss-120b131K$0.146 / $0.728$0.66
Uncensored gpt-oss-20b—$0.16 / $0.72$0.68
Uncensored GPT 6.2 SOL—$0.1765 / $0.8824$0.79
Uncensored Nemotron 3.5 Super VL—$0.225 / $0.75$0.83
Uncensored Qwen Long—$0.2192 / $0.8767$0.88

Live from the catalog on 2026-11-20, ordered by the cost of 1,000 turns of 2,000 input and 500 output tokens. Every model.

Uncensored gpt-oss-120b in OpenCode and Cline: what to set

The three fields are the base URL, the key and the model id, as in the settings above. What differs by build is the reply length, the reasoning switch and the context size, and those decide both whether a reply arrives whole and what each message costs.

  • Set the context size up to 131,072 tokens, the window the catalog lists for gpt-oss-120b-uncensored. Every message resends the context, so set it to what the chat needs rather than the maximum.
  • No jailbreak preamble is needed and none should be sent: a preamble is resent and billed on every message, and this build answers without one.

A request that fails before the model answers is not billed. A refusal written as ordinary text is billed like any answer, which is the reason to send this build rather than a stock model with a preamble.

What Uncensored gpt-oss-120b costs by client

SessionWhat is sentAt the live price
A month of short turns1,000 turns of 2,000 input and 500 output tokens$0.656
A coding day in OpenCode or Cline40 requests of 6,000 input and 1,200 output tokens$0.07
One long document, summarised once100,000 input and 1,000 output tokens in one request$0.0153

Input and output tokens at the price above, read from the catalog on 2026-11-20, with no prompt caching assumed; cached input bills at the cached rate, or at the input rate on a model without one. The balance is prepaid and each request settles at these rates.

Uncensored gpt-oss-120b questions

What is Uncensored gpt-oss-120b?

Uncensored gpt-oss-120b is a house build, with a 131,072-token context window, taking text input. On PentestLLM it answers as gpt-oss-120b-uncensored.

Is there a subscription for Uncensored gpt-oss-120b?

No. Credit is prepaid from $10 and billed per token: input $0.146 and output $0.728 per million tokens, cached input $0.146 (input rate).

What does a short chat turn on Uncensored gpt-oss-120b cost?

About $0.0005 for 1,000 tokens in and 500 tokens out, at $0.146 in and $0.728 out per million tokens.

Is Uncensored gpt-oss-120b OpenAI-compatible?

Yes. Send gpt-oss-120b-uncensored as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.pentestllm.ai/v1.

How do I use Uncensored gpt-oss-120b in a pentest or coding agent?

Set the agent's OpenAI-compatible provider to base URL https://api.pentestllm.ai/v1, paste your key and use gpt-oss-120b-uncensored as the model. The same three values work in OpenCode, Cursor, Cline, aider and PentestGPT; the guides show where each goes. See the setup guides.

Did Uncensored gpt-oss-120b pass the daily real-model check?

Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. Uncensored gpt-oss-120b’s latest result, from Oct 28: steady since Oct 21. See the daily check.

What is Uncensored gpt-oss-120b based on?

OpenAI's GPT-OSS 120B: 117B total, 5.1B active, open weights under Apache-2.0 (openai/gpt-oss-120b, read 2026-10-26). This build is that model served without a content filter.

What license does Uncensored gpt-oss-120b have?

The stock GPT-OSS 120B is released under Apache-2.0 (openai/gpt-oss-120b on Hugging Face, read 2026-10-26). Uncensored gpt-oss-120b is a build of those weights; sending gpt-oss-120b-uncensored here needs no copy of them.

Is there an uncensored GPT-OSS 120B API?

Yes: gpt-oss-120b-uncensored at https://api.pentestllm.ai/v1 on the OpenAI format, $0.146 / $0.728 per million tokens in / out, from prepaid credit with no subscription. Point your agent or the OpenAI SDK at that base URL with your key and this model id.

Is there a free or subscription Uncensored gpt-oss-120b API?

Neither: it is prepaid credit from $10, billed per token, with no monthly fee. One reply of 300 tokens on 4,000 tokens of context costs about $0.0008 at the live price, and 100 such replies $0.0802.

Can I download Uncensored gpt-oss-120b and run it locally?

The stock GPT-OSS 120B is open weights (117B total, 5.1B active, Apache-2.0 on openai/gpt-oss-120b, read 2026-10-26), and community uncensored conversions are published on Hugging Face at the same size. Sending gpt-oss-120b-uncensored to https://api.pentestllm.ai/v1 needs no download and no GPU: 100 replies cost $0.0802 at the live price.

What does Uncensored gpt-oss-120b cost per 100 messages?

$0.0656 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.146 input and $0.728 output per million tokens, from prepaid credit with no subscription.

Read next

Help