Skip to content

Cyber Frontier, per token on one key.

Cyber Frontier is a build set up for security work. It costs $5.25 per million input tokens and $15.75 per million output tokens, prepaid, with a 1,048,576-token context window. Call it at https://api.pentestllm.ai/v1/chat/completions with model "cyber-frontier" and a PentestLLM key, from any OpenAI SDK or agent that takes a base URL. It is for authorized security testing only.

Get a key

Security on PentestLLM as cyber-frontier.

Price per million tokens

Input
$5.25
Cached input
$0.9625
Output
$15.75
Daily check
Not checked yet
How the check works
As of
2026-11-11

First request

curl
curl https://api.pentestllm.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-ptl-live-…" \
  -H "Content-Type: application/json" \
  -d '{"model": "cyber-frontier", "messages": [{"role": "user", "content": "Hello"}]}'

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

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 cyber-frontier as the model. The same key calls every model on PentestLLM.

Cyber Frontier settings for a coding agent

Any agent that takes an OpenAI-compatible provider uses these values. Step-by-step setup per agent is under agents.

provider settings
Provider
OpenAI-compatible
Base URL
https://api.pentestllm.ai/v1
Model
cyber-frontier
Context window
1,048,576 tokens
Max output
65,536 tokens
Tool calling
yes, per the catalog
Key prefix
sk-ptl-

Cyber Frontier specs

Kind
Security
Context window
1,048,576 tokens
Max output
65,536 tokens
Input
text
Wire formats
openai
Endpoints
/v1/chat/completions, /v1/messages, /v1/completions, /v1/responses, /v1beta/models/{model}:generateContent

What Cyber Frontier is for

Cyber Frontier is set up for security work, so it takes on the questions a penetration tester, red team or bug bounty hunter brings where a stock assistant often declines: triaging scanner output, explaining a CVE, reviewing code for vulnerabilities, drafting report findings, writing detection rules and solving CTF challenges.

Use it only on systems you own or have written permission to test. The acceptable use policy lists what is not allowed and applies to every request.

Every request is 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 “not checked yet”. Call it from the OpenAI SDK or a coding agent, or send auto/security and let the router pick a security build per request. Keys and top-ups live in the console.

What Cyber Frontier costs, worked

An agent turn of 8,000 input and 1,000 output tokens at $5.25 input and $15.75 output per million tokens is $0.0578; 100 turns are $5.775 and 1,000 turns are $57.75. An agent resends its context on every turn, so the input side is most of the bill. All from prepaid credit, no subscription.

usage, 1,000 agent turns on Cyber Frontier
Input, 8,000 tokens at $5.25 per million
$0.042
Output, 1,000 tokens at $15.75 per million
$0.0158
One turn
$0.0578
1,000 turns
$57.75
Security buildsContextIn / out per 1M1,000 agent turns
Gemma 4 26B A4B Cybersecurity262K$0.4224 / $1.3376$4.7168
Qwen3.8 27B Cybersecurity262K$0.40 / $2.40$5.60
GLM-5.3 Flash Cybersecurity1049K$0.5093 / $1.6975$5.7715
Red Team (Flash)n/a$0.90 / $3.00$10.1999
Red Team (Pro)n/a$1.50 / $6.00$18.00
OrcaCyber MiniMax M3.1 Flash262K$2.00 / $4.00$20.00
OrcaCyber MiniMax M3.1 Flash262K$2.00 / $4.00$20.00
OrcaCyber Qwen3.8 Flash Next262K$2.00 / $4.00$20.00
OrcaCyber Qwen3.8 Flash Next262K$2.00 / $4.00$20.00
Cyber Frontier1049K$5.25 / $15.75$57.75
OrcaCyber Zero 1.5999K$7.50 / $18.75$78.75

Live from the catalog on 2026-11-11, ordered by the cost of 1,000 turns of 8,000 input and 1,000 output tokens; cached input is not counted. Every price.

Also try

Cyber Frontier questions

Cyber Frontier is a build set up for security work, with a 1,048,576-token context window. On PentestLLM it answers as cyber-frontier.

Authorized security work: triaging scanner output, explaining a CVE, reviewing code for vulnerabilities, drafting report findings, writing detection rules and solving CTF challenges. Use it only on systems you own or have written permission to test. See the acceptable use policy.

No. Credit is prepaid from $10 and billed per token: input $5.25 and output $15.75 per million tokens, cached input $0.9625.

About $0.0578 for 8,000 tokens in and 1,000 tokens out, at $5.25 in and $15.75 out per million tokens. A thousand such turns are $57.75.

Yes. Send cyber-frontier as the model through the OpenAI SDK, or any agent that takes a custom OpenAI base URL, with base URL https://api.pentestllm.ai/v1. It also answers the Anthropic Messages API at the same host, so agents built on the Anthropic SDK can call it. See the docs.

Yes. The catalog lists tools among the parameters Cyber Frontier takes, so function calling works and a request can declare the gateway's server-side tools, which the docs list with their fees. See the docs.

Read next