Skip to content

Inkling Uncensored, per token on one key.

Inkling Uncensored is an uncensored build, set up to decline fewer requests than a stock model. It costs $2.13 per million input tokens and $12.1403 per million output tokens, prepaid, with a 262,144-token context window. Call it at https://api.pentestllm.ai/v1/chat/completions with model "inkling-uncensored" 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

Uncensored by Thinking Machines, on PentestLLM as inkling-uncensored.

Price per million tokens

Input
$2.13
Cached input
$1.065
Output
$12.1403
Daily check
Steady since Nov 3
How the check works
As of
2026-11-12

First request

curl
curl https://api.pentestllm.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-ptl-live-…" \
  -H "Content-Type: application/json" \
  -d '{"model": "inkling-uncensored", "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 inkling-uncensored as the model. The same key calls every model on PentestLLM.

Inkling Uncensored 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
inkling-uncensored
Context window
262,144 tokens
Max output
65,536 tokens
Tool calling
yes, per the catalog
Key prefix
sk-ptl-

Inkling Uncensored specs

Kind
Uncensored
Developer
Thinking Machines
Context window
262,144 tokens
Max output
65,536 tokens
Input
text and image
Wire formats
openai
Endpoints
/v1/chat/completions, /v1/messages, /v1/completions, /v1/responses, /v1beta/models/{model}:generateContent

What Inkling Uncensored is for

Inkling Uncensored is an uncensored build: it is set up to decline fewer security questions than the stock model. Refusals are reduced, not gone. Testers use it for 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 “Steady since Nov 3”. 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 Inkling Uncensored costs, worked

An agent turn of 8,000 input and 1,000 output tokens at $2.13 input and $12.1403 output per million tokens is $0.0292; 100 turns are $2.918 and 1,000 turns are $29.1803. 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 Inkling Uncensored
Input, 8,000 tokens at $2.13 per million
$0.017
Output, 1,000 tokens at $12.1403 per million
$0.0121
One turn
$0.0292
1,000 turns
$29.1803
Uncensored buildsContextIn / out per 1M1,000 agent turns
GLM-5.3 Flash Uncensoredn/a$0.1053 / $0.3685$1.2107
GLM-5.3 Uncensoredn/a$0.282 / $0.846$3.102
Dolphin Mistral 24B Venice Edition33K$0.50 / $2.25$6.25
Deepseek V4.1 Flash Uncensored1000K$0.5412 / $2.5882$6.9176
Gemma 4 26B-A4B Uncensored33K$0.60 / $2.80$7.60
Jailbreak-Free Assistant1049K$0.75 / $2.50$8.50
SuperGemma 4 26B Uncensored256K$0.78 / $2.40$8.64
Amoral Gemma3 27B v233K$1.05 / $1.05$9.45
Gemma 4 31B K1 v5262K$1.071 / $1.071$9.639
DeepSeek V4 Pro Uncensoredn/a$0.97 / $1.94$9.70
DeepSeek V4.1 Flash 0910 Uncensored524K$0.825 / $3.30$9.90
Inkling Uncensored262K$2.13 / $12.1403$29.1803

Live from the catalog on 2026-11-12, ordered by the cost of 1,000 turns of 8,000 input and 1,000 output tokens with no prompt caching assumed; cached input bills at the cached rate, or at the input rate on a model without one. Every price.

Also try

Inkling Uncensored questions

Inkling Uncensored is an uncensored build, set up to decline fewer requests than a stock model, from Thinking Machines, with a 262,144-token context window. On PentestLLM it answers as inkling-uncensored.

Inkling Uncensored is set up to decline fewer requests than the stock model, which is what security testers need when a general assistant refuses a question about a vulnerability or a tool. Refusals are reduced, not gone, and the acceptable use policy still applies to every request. See the acceptable use policy.

No. Credit is prepaid from $10 and billed per token: input $2.13 and output $12.1403 per million tokens, cached input $1.065.

About $0.0292 for 8,000 tokens in and 1,000 tokens out, at $2.13 in and $12.1403 out per million tokens. A thousand such turns are $29.1803.

Yes. Send inkling-uncensored 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 Inkling Uncensored 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.

Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. Inkling Uncensored’s latest result, from Nov 12: steady since Nov 3. See the daily check.

Read next