An unrestricted.sh alternative
unrestricted.sh is a pay-as-you-go API with a short list of uncensored open-weight models for security research; PentestLLM is the alternative when you want a wider catalog with security-tuned builds and a router that picks one per request. One prepaid key from $10 reaches 9 security-tuned builds, with abliterated and uncensored builds beside them.
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."}]
}'
What unrestricted.sh is, as of November 2026
The site unrestricted.sh, read on 11 November 2026, describes itself as AI for security research with zero data retention. It sells open-weight language models for security research, vulnerability assessment and software engineering, billed per token, behind one API it calls OpenAI-compatible and Anthropic-compatible at https://api.unrestricted.sh/v1. The page says prompts and replies are never saved or logged, that the company is Danish, and that its Qwen model runs on its own GPUs while the other models are partner-hosted.
Its pricing page on the same day listed four models, each labelled Uncensored: Qwen3.8 27B at $0.50 per million input tokens and $1.00 per million output tokens with a 262K context, and GLM-5.3 Flash, MiMo V2.6 Flash and DeepSeek V4.1 Flash 1017 with 1M contexts and input prices from $0.25 per million tokens. Top-ups start at $5 by card, Apple Pay, Google Pay or Link, purchased credit does not expire, and a new account gets $0.50 of welcome credit that lapses after 72 hours. The page describes a $0.01 wake fee when an idle model has to start. It mentions Pro and Max plans only in a line about concurrent requests and gives no price for either.
On the day we read it the home page also said signups were closed for now. Its guides page covers thirteen coding tools, among them OpenCode, Codex CLI, Aider and Cline. That is what its pages show; we have not used the service and do not compare its answers with anything here.
Where the two differ
- Catalog
- unrestricted.sh listed four uncensored models in November 2026. PentestLLM lists 9 security-tuned builds, with abliterated and uncensored builds beside them.
- Picking a model
- PentestLLM has
auto/security, which routes each request to a fast, balanced or frontier security build and bills at that build’s price. You can still name a build yourself. - Server tools
- PentestLLM runs web search ($0.01 per search), page fetch ($0.001 per page fetched), a code sandbox ($0.05 per container-hour, 1-minute minimum) and remote MCP (No tool fee) on the API side when a request declares them. We did not find server-side tools described on the unrestricted.sh pages we read.
- Smallest top-up
- unrestricted.sh: $5, per its pricing page. PentestLLM: $10, by card.
- Data handling
- unrestricted.sh leads with zero data retention. Read each service’s privacy page and compare it against your engagement rules.
Both are prepaid, per-token APIs that need no subscription. The difference is the breadth of the catalog and what the API does beyond returning tokens.
What PentestLLM serves
PentestLLM is a model API and nothing else: no chat app, no agent, no scanner. It serves 9 security-tuned builds, plus abliterated and uncensored builds, behind an OpenAI-compatible endpoint at https://api.pentestllm.ai/v1 and an Anthropic-compatible Messages endpoint on the same key. The largest context window listed today is 1M tokens. Every listed model is called for real once a day, and the models page and pricing page show the live figures.
The builds are tuned or abliterated to answer security questions other models decline. Expect reduced refusals, not none, and expect the acceptable use policy to apply to every request.
Moving a client across
Both services speak the OpenAI wire format, so a client that works with one needs three changes to work with the other: the base URL, the key and the model id. Set the base URL to https://api.pentestllm.ai/v1, create a key in the PentestLLM console, and use auto/security or a named build from the models page. The agent guides give the exact fields for OpenCode, Cline, aider and Claude Code.
What it costs
There is no subscription. The balance is prepaid from $10 by card and spent per token. On 2026-11-12 input prices for security builds start at $0.40 per million tokens, and the table below lists every security build with its live price. A request sent to auto/security is billed at the price of the build that answered, and the response names that build.
When unrestricted.sh is the better choice
If zero data retention is your first requirement, unrestricted.sh puts that claim at the top of its page and describes where each model is hosted; read its no-logs policy and judge it against your needs. If you want one of the open-weight models it lists and a $5 entry point, it is a direct fit, provided signups have reopened when you read this. PentestLLM suits testers who want security-tuned builds, a router and server-side tools on one key.
Both services say the same thing about scope. Its acceptable use page allows security testing with permission and prohibits attacks on systems you may not test; ours limits use to authorized work on systems you own or have written permission to test.
9 security 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 |
|---|---|---|---|
| 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
Per its own site in November 2026, a pay-as-you-go API serving uncensored open-weight models for security research, with an OpenAI-compatible and Anthropic-compatible endpoint and a zero data retention claim.
On 11 November 2026 its pricing page listed four models with input prices from $0.25 to $0.50 per million tokens, a $5 minimum top-up and no subscription. Check unrestricted.sh for current prices.
Yes. Both expose an OpenAI-compatible endpoint, so you change the base URL, the key and the model id. PentestLLM also has an Anthropic-compatible Messages endpoint on the same key.
Some builds are security-tuned and some are abliterated or uncensored. All of them answer security questions more often than general models do, which is reduced refusals, not none, and they are for authorized testing only.
Per token from a prepaid balance with a $10 minimum top-up by card and no subscription. On 2026-11-12 input prices for security builds start at $0.40 per million tokens.
Read next
- RedRouter alternativePrepaid per-token security models, next to a low-refusal router with plans.
- abliteration.ai alternativeMany abliterated and security builds per token, next to a monthly plan.
- Uncensored LLM APIThe endpoints, wire formats and per-token billing behind the uncensored builds.
- Uncensored LLM for pentestingWhat abliterated and security-tuned builds change for authorized penetration testing.
Facts about other products and tools on this page were read from their own pages on 11 November 2026: unrestricted.sh, unrestricted.sh pricing, unrestricted.sh guides, unrestricted.sh acceptable use. 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