A WhiteRabbitNeo alternative by API
WhiteRabbitNeo began as an open-source security model; it has since become Deep Hat, a model that runs inside Kindo’s platform. PentestLLM is an alternative for people who want security-tuned models as a self-serve API: 9 builds on one prepaid key from $10, billed per token.
curl https://api.pentestllm.ai/v1/chat/completions \
-H "Authorization: Bearer sk-ptl-live-…" \
-H "Content-Type: application/json" \
-d '{
"model": "auto/security",
"messages": [{"role": "user", "content": "Rank these scanner findings by severity and say what to verify first."}]
}'
WhiteRabbitNeo today, as of November 2026
On 11 November 2026 the address whiterabbitneo.com redirected to deephat.ai. That page says Deep Hat, formerly WhiteRabbitNeo, is Kindo’s cybersecurity model, that it began as an open-source project and has become a proprietary model that runs inside Kindo, and that the original open-source project remains available for reference. It links to a Hugging Face organization, offers a way to try the model for free and invites enterprises to book a demo.
The page we read lists no prices and does not describe a public API endpoint. We state nothing about Deep Hat’s quality or benchmarks; the vendor’s page is the place for those.
Three ways to get a security model
- Run open weights
- Download a model and serve it on your own GPU. Full control, your hardware, your maintenance.
- Use a platform
- Adopt a vendor’s environment where the model lives, usually through a sales conversation.
- Call an API
- Send requests to a hosted endpoint and pay for the tokens. No hardware and no contract.
PentestLLM is the third. It does not host WhiteRabbitNeo or Deep Hat; it hosts other security-tuned builds, listed on the models page.
What you get on the API
An OpenAI-compatible endpoint at https://api.pentestllm.ai/v1 and an Anthropic-compatible Messages endpoint, on the same key. The id auto/security routes each request to a fast, balanced or frontier security build and bills it at that build’s own price. The largest context window listed today is 1M tokens.
The builds are tuned or abliterated to answer security questions other models decline. As with any such model, that means reduced refusals, not zero.
If you were running WhiteRabbitNeo locally
Tools that talked to a local OpenAI-compatible server need only a new base URL, a key and a model id to talk to this API. Agents are covered in the guides: OpenCode, Cline and aider all take an OpenAI-compatible endpoint.
What changes is where the prompt goes. A local model keeps everything on your machine; an API does not. Read the privacy page and decide what your engagement rules let you send. For work that must stay on an isolated network, a local model is still the right tool.
Cost against a GPU
A local model costs a graphics card and electricity whether or not you use it. An API costs nothing idle and a few cents to dollars per session busy. The table below is the live catalog on 2026-11-11, with input prices from $0.40 per million tokens. PentestLLM is for authorized security work only, on systems you own or have written permission to test; see the acceptable use policy.
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
In November 2026 whiterabbitneo.com redirects to deephat.ai, which says Deep Hat was formerly WhiteRabbitNeo and that the original open-source project remains available for reference.
The Deep Hat page we read in November 2026 does not describe a public API endpoint or list prices. PentestLLM does not host WhiteRabbitNeo or Deep Hat; it offers other security-tuned builds through an OpenAI-compatible API.
You send requests to a hosted endpoint and pay per token instead of buying and running a GPU. Larger builds and long context windows are available, and prompts leave your machine, which matters for some engagements.
No. Create a key in the console and add credit from $10 by card or crypto.
They are security-tuned or abliterated, so they answer security questions that general models decline. The honest term is reduced refusals, and the acceptable use policy applies to every request.
Read next
- Uncensored LLM for pentestingWhat abliterated and security-tuned builds change for authorized penetration testing.
- Cybersecurity LLM APIThe API itself: endpoints, the auto/security router, server tools and per-token prices.
- HackerGPT alternativePay-per-token security models with an API, next to the hosted assistants.
- Penligent alternativeModels for your own agent and scripts, next to a packaged pentest app.
Facts about other products and tools on this page were read from their own pages on 11 November 2026: deephat.ai (whiterabbitneo.com redirects here). 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