Field manual · AI for authorized security testing · Edition November 2026 · Updated 2026-11-18

Models · Ranked

Best LLM for pentesting: five models, ranked by phase

The best LLM for pentesting is Kimi K3.1 Pro, an abliterated 2,780B model with 1M tokens of context that reads images and video.

GLM-5.3 is the text second, and DeepSeek V4.1 Flash handles volume at $0.24 in and $0.90 out per 1M tokens.

Updated November 18, 2026Authorized work only
01Ranking

The five models

Specs and prices per 1M tokens from Silk Compute and Hugging Face, read November 18, 2026.

01

Kimi K3.1 Pro

Best AI model for pentesting · Moonshot AI

The largest model here, at 2,780B parameters, for chaining findings, reading screenshots and long agent runs.

Attack-path analysisWeb applicationsActive DirectorySource code reviewLong agent runs
Maker
Moonshot AI
Size
2,780B
Price / 1M
$3.00 in · $8.00 out
Cached in
$0.30
Context
1,048,576
Max output
943,718
Inputs
text, images, video
API id
kimi-k3.1-pro-uncensored
02

GLM-5.3

Strong second for code and text · Z.ai

Z.ai's 753B text model, strong at software work, at $2.00 in and $4.00 out per 1M tokens.

Source code reviewCloud policy reviewToolingSecond opinions
Maker
Z.ai
Size
753B
Price / 1M
$2.00 in · $4.00 out
Cached in
$0.30
Context
1,048,576
Max output
131,072
Inputs
text
API id
glm-5.3-uncensored
03

DeepSeek V4.1 Flash 1017

Best value for volume work · DeepSeek

A 763B model at $0.24 in and $0.90 out per 1M tokens, the lowest blended price at Silk Compute, for recon and reports.

Recon triageReportingCTF practiceLong transcripts
Maker
DeepSeek
Size
763B
Price / 1M
$0.24 in · $0.90 out
Cached in
$0.038
Context
1,048,576
Max output
131,072
Inputs
text, images
API id
deepseek-v4.1-flash-1017-uncensored
04

GLM-5.3 Flash

Light and low-cost · Z.ai

A 320B model with 18B active parameters, at $0.24 in and $1.00 out, for first passes and image sorting.

First-pass triageBackground jobsScreenshot sorting
Maker
Z.ai
Size
320B total, 18B active
Price / 1M
$0.24 in · $1.00 out
Cached in
$0.06
Context
1,048,576
Max output
131,072
Inputs
text, images
API id
glm-5.3-flash-uncensored
05

Qwen 3.8 27B Abliterated

Best to run on one GPU · local

A 27.8B model that fits one 24 GB GPU or a 32 GB Mac at 4-bit, so client data stays on your machine.

Offline labsSensitive client dataReporting drafts
Size
27.8B
4-bit
about 17 GB
Runs on
one 24 GB GPU or a 32 GB Mac
License
Apache 2.0
Price
Hardware you control
02Criteria

What makes an LLM good for pentesting

Six checks, in this order.

Rank a model by whether it finishes the authorized task, then by size, the 1,048,576-token context, which inputs it reads, the price, and where the data stays. Kimi K3.1 Pro leads on size and inputs. DeepSeek V4.1 Flash is $0.24 in and $0.90 out. GLM-5.3 is text only. Retention is on the API ranking, and refusals are in uncensored AI for pentesting.

03Cost

What a job costs on each model

Kimi K3.1 Pro where judgment matters, DeepSeek V4.1 Flash for volume.

JobTokens in / outKimi K3.1 ProGLM-5.3DeepSeek V4.1 Flash 1017GLM-5.3 Flash
Recon triageScan output, read once400K / 10K$1.28$0.84$0.11$0.11
Attack-path analysisNotes in, ranked paths out150K / 20K$0.61$0.38$0.05$0.06
Report draftNotes in, findings out300K / 60K$1.38$0.84$0.13$0.13
Autonomous agent runA long tool loop5,000K / 150K$16.20$10.60$1.34$1.35

Silk Compute list prices per 1M tokens, read November 18, 2026, before cached input at $0.30, $0.30, $0.038, $0.06 in the same order.

04Not ranked

Models we leave out, and why

Claude, GPT and Gemini can stop authorized offensive work. The policy text is in why AI refuses pentesting.

Silk Compute serves Hy4 at $1.60 in and $3.20 out. It is not for exploit work, because Tencent left offensive exploitation data out of it. It suits defensive triage. Hermes 3 is a fine-tune, not an abliteration. The API ranking names who serves it. Strix's docs say "Most local models, especially those under 70B parameters, struggle with these complex tasks." (Strix docs)