Is OpenRouter uncensored?

It depends on the model and the provider. OpenRouter’s docs describe a per-model flag for whether content moderation is applied, and its error reference says a provider can request moderation that blocks a flagged request. It is a general router and does not describe itself as an uncensored service on the pages we read.

How much does OpenRouter cost?

On 11 November 2026 its pricing page said models are billed at the provider’s price with no markup, plus a platform fee on credit purchases of 5.5% on the Standard plan and 8% on Business. Check openrouter.ai for current terms.

Can I use PentestLLM and OpenRouter together?

Yes. Both are OpenAI-compatible, so one client can hold two provider entries. A sensible setup keeps a general model for everyday coding and sends security questions to a security build.

What does the PentestLLM router do?

The model id auto/security sends each request to a fast, balanced or frontier security build and bills it at that build’s price. The response names the build that answered.

What does PentestLLM cost?

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.

An OpenRouter alternative for security

OpenRouter is a general router that puts hundreds of models from many providers behind one API; PentestLLM is a specialist alternative whose catalog is built around security-tuned, abliterated and uncensored builds for authorized testing. One prepaid key from $10 reaches 9 security-tuned builds and a router, auto/security, that picks among them per request.

Get a key Prices per token

shell

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 OpenRouter is, as of November 2026

OpenRouter’s site, read on 11 November 2026, describes one API for text, image, video and audio models, with hundreds of models from many providers behind one key. Text models share an OpenAI-compatible endpoint at https://openrouter.ai/api/v1, and the service routes around provider outages and rate limits with automatic fallbacks. Its public model list returned 467 entries on the day we read it.

Its pricing page says there is no markup on the provider’s price, and that a platform fee is charged when you buy credits: 5.5% on the Standard pay-as-you-go plan and 8% on Business, with Enterprise terms through sales. A Free plan covers a set of free models with a daily request cap. Payment on the paid plans is by card, AliPay or USDC.

On moderation its docs are specific. Each model in the list carries a flag, is_moderated, documented as whether content moderation is applied; on 11 November 2026 that flag was set on 139 of the 467 entries. The error reference says a request can come back as a 403 when its input is flagged, and that the error names the provider that requested moderation. In other words, moderation is set per model and provider, not once for the whole service.

A general router or a security catalog

Catalog: OpenRouter: hundreds of general models across text, image, video and audio. PentestLLM: text builds for security work, 9 of them security-tuned, with abliterated and uncensored builds beside them.
Finding a model: On a general router, uncensored and security builds are a small part of a long list that you search yourself. On PentestLLM they are what the catalog is for.
Moderation: OpenRouter: flagged per model and requested by the provider, per its docs. PentestLLM: one acceptable use policy for every build.
Routing: OpenRouter’s home page describes fallback between providers when one is down or rate limited. PentestLLM’s auto/security picks a security build for the request: fast, balanced or frontier, billed at that build’s price.
Price: OpenRouter: the provider’s price plus a platform fee on credit purchases, per its pricing page. PentestLLM: a per-token price for each build, listed on the pricing page.

Why security work is a corner case there

A general router serves every kind of customer, and most of them are not testers. Its catalog reflects that. The frontier models that lead a general catalog are also the ones most likely to decline an offensive security question, and whether a given open model is filtered depends on which provider answers. When we searched OpenRouter’s public list for the word uncensored on 11 November 2026, two entries matched by name or summary. None of this is a fault. It is what a general service looks like from a specialist’s seat.

PentestLLM starts from the other end. The catalog is built for authorized security testing: builds tuned on security material, abliterated builds and uncensored builds. You do not filter a long list to find them, and the same acceptable use policy applies whichever build answers. Refusals are reduced, not removed.

What PentestLLM includes

An OpenAI-compatible endpoint at https://api.pentestllm.ai/v1 and an Anthropic-compatible Messages endpoint on the same key, with context windows up to 1M tokens. When a request declares them, 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) run on the API side. Every listed model is called for real once a day, and the models page shows the live list. The auto router page explains how auto/security chooses a tier.

Moving a client across

OpenRouter and PentestLLM both speak the OpenAI wire format. A client set up for one needs a new base URL, key and model id for the other: https://api.pentestllm.ai/v1, a key from the PentestLLM console, and auto/security or a named build. Nothing stops you keeping both, with a general router for everyday coding and this endpoint for the security work a general model declines. The agent guides show the fields for OpenCode, Cline and aider.

On 2026-11-12 input prices for security builds start at $0.40 per million tokens. The balance is prepaid from $10 by card, with no subscription.

When OpenRouter is the better choice

If you need many kinds of model on one bill, including image, video and audio models and the frontier models from the large labs, OpenRouter is built for that and PentestLLM is not. Its free models are a way to experiment at no cost, and its provider fallback is useful for production traffic. If the model you want for security work is on its list and not moderated, using it there is reasonable.

PentestLLM is for the narrower case: you want security and uncensored builds without searching for them, on a service whose stated purpose is authorized testing. Either way, test only 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

Full price list and tool fees · Every model · API docs

Questions

It depends on the model and the provider. OpenRouter’s docs describe a per-model flag for whether content moderation is applied, and its error reference says a provider can request moderation that blocks a flagged request. It is a general router and does not describe itself as an uncensored service on the pages we read.
On 11 November 2026 its pricing page said models are billed at the provider’s price with no markup, plus a platform fee on credit purchases of 5.5% on the Standard plan and 8% on Business. Check openrouter.ai for current terms.
Yes. Both are OpenAI-compatible, so one client can hold two provider entries. A sensible setup keeps a general model for everyday coding and sends security questions to a security build.
The model id auto/security sends each request to a fast, balanced or frontier security build and bills it at that build’s price. The response names the build that answered.
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.

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.

Get a key

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 CybersecurityOrcaCyber Zero 1.5 $18.75