Run Uncensored Grok 4.3 without a GPU.
House build on PentestLLM as grok-4.3-uncensored.
Uncensored Grok 4.3 is an PentestLLM house build. It costs $1.875 per million input tokens and $3.75 per million output tokens, prepaid. Call it at https://api.pentestllm.ai/v1/chat/completions with model "grok-4.3-uncensored" and an PentestLLM key, from any OpenAI SDK or client that takes a base URL.
Price and first request
Price per million tokens
- Input
- $1.875
- Cached input
- $0.30
- Output
- $3.75
- Daily check
- Not checked yet
- As of
- 2026-11-20
First request
curl https://api.pentestllm.ai/v1/chat/completions \ -H "Authorization: Bearer sk-ptl-live-…" \ -H "Content-Type: application/json" \ -d '{"model": "grok-4.3-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'Uncensored Grok 4.3 specs
- Kind
- House build
- Tool calling
- Yes, for agents
- Wire formats
- openai
Get a key
- Create a key in the console. Credit is prepaid from $10, with no subscription.
- Set OPENAI_BASE_URL to https://api.pentestllm.ai/v1 and send your sk-ptl- key as the bearer token.
- Send grok-4.3-uncensored as the model. The same key calls every model on PentestLLM.
Uncensored Grok 4.3 settings for OpenCode and Cline
- Provider
- OpenAI-compatible
- Base URL
- https://api.pentestllm.ai/v1
- Model
- grok-4.3-uncensored
- Context window
- not in the catalog
- Key prefix
- sk-ptl-
What Uncensored Grok 4.3 is
- Weights
- not published for this build
From the SDK
from openai import OpenAI client = OpenAI(base_url="https://api.pentestllm.ai/v1", api_key="sk-ptl-live-…") completion = client.chat.completions.create( model="grok-4.3-uncensored", messages=[{"role": "user", "content": "Hello"}],)print(completion.choices[0].message.content)import OpenAI from 'openai'; const client = new OpenAI({ baseURL: 'https://api.pentestllm.ai/v1', apiKey: 'sk-ptl-live-…' }); const completion = await client.chat.completions.create({ model: 'grok-4.3-uncensored', messages: [{ role: 'user', content: 'Hello' }],});console.log(completion.choices[0].message.content);What Uncensored Grok 4.3 answers
Uncensored Grok 4.3 is an uncensored build: it answers without the safety refusals of the stock model.
Every request is routed to the build’s live route and 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”.
Use it from the OpenAI SDK, or from a coding or pentest agent. Keys and top-ups live in the console: top up by card, WeChat Pay or Alipay.
More house builds
What Uncensored Grok 4.3 costs, worked
A chat turn of 2,000 input and 500 output tokens at $1.875 input and $3.75 output per million tokens is $0.0056; 1,000 turns are $5.63. A long chat session of 100 replies of 300 tokens costs $0.8625 at 4,000 tokens of context and $3.1125 at 16,000: every message resends the context, so size it to what the chat needs. All from prepaid credit, no subscription.
| House build builds | Context | In / out per 1M | 1,000 chat turns |
|---|---|---|---|
| Uncensored GLM 5.3 FlashX | — | $0.045 / $0.15 | $0.17 |
| Uncensored GPT-6 Luna | — | $0.0625 / $0.20 | $0.23 |
| Uncensored DeepSeek V4 Flash 0731 | 262K | $0.084 / $0.12 | $0.23 |
| Uncensored GPT-5.6 Luna | — | $0.06 / $0.36 | $0.30 |
| Uncensored Claude Haiku 5 5 | — | $0.0735 / $0.40 | $0.35 |
| Uncensored GPT-4.1 Nano | — | $0.10 / $0.40 | $0.40 |
| Uncensored Qwen3.8 Flash | — | $0.1152 / $0.361 | $0.41 |
| Uncensored Agnes 3.0 Flash | — | $0.12 / $0.36 | $0.42 |
| Uncensored Qwen2.5 7B Instruct | — | $0.20 / $0.20 | $0.50 |
| Uncensored GPT-4o mini | — | $0.15 / $0.60 | $0.60 |
| Uncensored Doubao Seed 2.0 Mini | — | $0.096 / $0.896 | $0.64 |
| Uncensored gpt-oss-120b | 131K | $0.146 / $0.728 | $0.66 |
| Uncensored gpt-oss-20b | — | $0.16 / $0.72 | $0.68 |
| Uncensored Qwen3.8 27b Swift | — | $1.00 / $6.00 | $5.00 |
| Uncensored Grok 4.3 | — | $1.875 / $3.75 | $5.63 |
| Uncensored Kimi K2.6 | 262K | $1.17 / $7.34 | $6.01 |
Uncensored Grok 4.3 in OpenCode and Cline: what to set
The three fields are the base URL, the key and the model id, as in the settings above. What differs by build is the reply length, the reasoning switch and the context size, and those decide both whether a reply arrives whole and what each message costs.
- The catalog lists no context window for grok-4.3-uncensored; keep the context size your client already uses.
- No jailbreak preamble is needed and none should be sent: a preamble is resent and billed on every message, and this build answers without one.
A request that fails before the model answers is not billed. A refusal written as ordinary text is billed like any answer, which is the reason to send this build rather than a stock model with a preamble.
What Uncensored Grok 4.3 costs by client
| Session | What is sent | At the live price |
|---|---|---|
| A month of short turns | 1,000 turns of 2,000 input and 500 output tokens | $5.625 |
| A coding day in OpenCode or Cline | 40 requests of 6,000 input and 1,200 output tokens | $0.63 |
| One long document, summarised once | 100,000 input and 1,000 output tokens in one request | $0.1913 |
Uncensored Grok 4.3 questions
What is Uncensored Grok 4.3?
Uncensored Grok 4.3 is a house build. On PentestLLM it answers as grok-4.3-uncensored.
Is there a subscription for Uncensored Grok 4.3?
No. Credit is prepaid from $10 and billed per token: input $1.875 and output $3.75 per million tokens, cached input $0.30.
What does a short chat turn on Uncensored Grok 4.3 cost?
About $0.0038 for 1,000 tokens in and 500 tokens out, at $1.875 in and $3.75 out per million tokens.
Is Uncensored Grok 4.3 OpenAI-compatible?
Yes. Send grok-4.3-uncensored as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.pentestllm.ai/v1.
How do I use Uncensored Grok 4.3 in a pentest or coding agent?
Set the agent's OpenAI-compatible provider to base URL https://api.pentestllm.ai/v1, paste your key and use grok-4.3-uncensored as the model. The same three values work in OpenCode, Cursor, Cline, aider and PentestGPT; the guides show where each goes. See the setup guides.
What is Uncensored Grok 4.3 based on?
No base model, parameter count or training notes are published for Uncensored Grok 4.3.
What does Uncensored Grok 4.3 cost per 100 messages?
$0.5625 for 100 chat turns of 2,000 input and 500 output tokens each, at $1.875 input and $3.75 output per million tokens, from prepaid credit with no subscription.