A HackerGPT alternative with an API
HackerGPT-style products are hosted assistants: you chat in their interface and pay by plan. PentestLLM is the alternative for people who want the model itself, with 9 security-tuned builds behind an OpenAI-compatible and Anthropic-compatible API, billed per token from a prepaid balance.
from openai import OpenAI
client = OpenAI(base_url="https://api.pentestllm.ai/v1", api_key="sk-ptl-live-…")
reply = client.chat.completions.create(
model="auto/security",
messages=[{"role": "user", "content": "Explain this advisory and list what to check on an affected host."}],
)
print(reply.model) # the build that answered
print(reply.choices[0].message.content)
What the name points to, as of November 2026
More than one product answers to HackerGPT. The site hackergpt.app, read on 11 November 2026, describes HackerGPT as an OSINT and CTF solving tool, and its GitHub repository describes an offensive security companion with that site as its lite version.
A similarly named hosted product is HackerAI at hackerai.co, which describes itself as an AI-powered penetration testing assistant with its source code public on GitHub. Its pricing page on the same day listed a Free plan, Pro at $29 a month, Pro+ at $60, Ultra at $200 and Team at $40 a seat each month, with lower prices on yearly billing. The page describes an agent mode with a local sandbox on the Free plan and cloud agents from Pro up. Neither its home page nor its pricing page mentioned an API when we read them.
Hosted assistant or model API
- Interface
- A hosted assistant gives you its chat and agent. An API gives you the model in whatever you already use.
- Billing
- A plan is a fixed monthly price with included usage. Per-token billing charges for the requests you sent.
- Automation
- An API can be called from scripts, CI jobs and your own tools.
- Model choice
- On an API you pick the build per request, or let a router pick.
Neither shape is better in general. They suit different ways of working.
What PentestLLM gives you
One key, prepaid from $10 by card or crypto. Requests go to https://api.pentestllm.ai/v1 in the OpenAI format or to the Messages endpoint in the Anthropic format. The id auto/security routes each request to a fast, balanced or frontier security build and bills it at that build’s price, and the response names the build that answered.
When a request declares them, the API runs web search ($0.01 per search), page fetch ($0.001 per page fetched) and a code sandbox ($0.05 per container-hour, 1-minute minimum) on its side. The builds are tuned or abliterated to answer security questions other models decline; expect reduced refusals, not none.
When a hosted assistant is the better choice
If you want to open a browser tab and start, with file uploads and an agent sandbox someone else maintains, a hosted assistant does that and an API does not. If your usage is steady, a fixed plan is easy to budget. Choose the API when you live in a terminal or an editor, when you want to script the model, or when your usage is uneven and a monthly plan would sit idle.
Getting started
Create a key in the console, add credit, and follow one of the agent guides: OpenCode for a terminal, Cline for an editor. The live price of every security build is in the table below. PentestLLM is for systems you own or have written permission to test; the acceptable use policy has the detail.
9 security builds, priced per token
Read from the live catalog on 2026-11-11. 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 |
|---|---|---|---|
| Qwen3.8 27B Cybersecurity | $0.40 | $2.40 | 262,144 |
| Gemma 4 26B A4B Cybersecurity | $0.4224 | $1.3376 | 262,144 |
| GLM-5.3 Flash Cybersecurity | $0.5093 | $1.6975 | 1,048,576 |
| Red Team (Flash) | $0.90 | $3.00 | not published |
| Red Team (Pro) | $1.50 | $6.00 | not published |
| OrcaCyber MiniMax M3.1 Flash | $2.00 | $4.00 | 261,632 |
| OrcaCyber Qwen3.8 Flash Next | $2.00 | $4.00 | 261,632 |
| Cyber Frontier | $5.25 | $15.75 | 1,048,576 |
| OrcaCyber Zero 1.5 | $7.50 | $18.75 | 999,488 |
Questions
We describe each from its own site. In November 2026 hackergpt.app presents HackerGPT as an OSINT and CTF solving tool, and hackerai.co presents HackerAI as an AI-powered penetration testing assistant. We make no claim about how the two are related.
On 11 November 2026 its pricing page listed Free, Pro at $29 a month, Pro+ at $60, Ultra at $200 and Team at $40 a seat each month, with lower yearly prices. Check hackerai.co for current plans.
PentestLLM is an API. You use it through an agent, an editor extension, an SDK or curl. The agent guides cover the common clients.
There is no subscription and no free plan; the balance is prepaid from $10. On 2026-11-11 input prices for security builds start at $0.40 per million tokens, so a small top-up covers a lot of testing.
They are tuned or abliterated to answer security questions other models decline, for authorized testing. Refusals are reduced, not eliminated.
Read next
- PentestGPT alternativeThe model endpoint to run PentestGPT on, or to use in place of a chat subscription.
- Kali GPT alternativeSecurity models in the terminal agents you already run on Kali.
- Penligent alternativeModels for your own agent and scripts, next to a packaged pentest app.
- Hacker AISecurity-tuned models by API for ethical hacking and authorized testing.
Facts about other products and tools on this page were read from their own pages on 11 November 2026: hackergpt.app, HackerGPT on GitHub, hackerai.co, hackerai.co pricing. They change; check the source before relying on a figure.
One key, from $10
PentestLLM is for systems you own or have written permission to test. The acceptable use policy says what is not allowed.
- 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