Run Llama 3.3 70B Instruct (Uncensored) without a GPU.
Uncensored by Meta, on PentestLLM as llama-3.3-70b-instruct-uncensored.
Llama 3.3 70B Instruct (Uncensored) is an uncensored build of Llama 3.3 70B Instruct. It costs $0.40 per million input tokens and $1.28 per million output tokens, prepaid. Call it at https://api.pentestllm.ai/v1/chat/completions with model "llama-3.3-70b-instruct-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
- $0.40
- Cached input
- $0.20
- Output
- $1.28
- Daily check
- Steady since Nov 18
- 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": "llama-3.3-70b-instruct-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'Llama 3.3 70B Instruct (Uncensored) specs
- Kind
- Uncensored
- Developer
- Meta
- Base model
- Llama 3.3 70B Instruct
- 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 llama-3.3-70b-instruct-uncensored as the model. The same key calls every model on PentestLLM.
Llama 3.3 70B Instruct (Uncensored) settings for OpenCode and Cline
- Provider
- OpenAI-compatible
- Base URL
- https://api.pentestllm.ai/v1
- Model
- llama-3.3-70b-instruct-uncensored
- Context window
- not in the catalog
- Key prefix
- sk-ptl-
What Llama 3.3 70B Instruct (Uncensored) is
- Developer
- Meta
- 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="llama-3.3-70b-instruct-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: 'llama-3.3-70b-instruct-uncensored', messages: [{ role: 'user', content: 'Hello' }],});console.log(completion.choices[0].message.content);What changed from stock Llama 3.3 70B Instruct
Llama 3.3 70B Instruct (Uncensored) 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 “Steady since Nov 18”.
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.
Also try
More from Meta
What Llama 3.3 70B Instruct (Uncensored) costs, worked
A chat turn of 2,000 input and 500 output tokens at $0.40 input and $1.28 output per million tokens is $0.0014; 1,000 turns are $1.44. A long chat session of 100 replies of 300 tokens costs $0.1984 at 4,000 tokens of context and $0.6784 at 16,000: every message resends the context, so size it to what the chat needs. All from prepaid credit, no subscription.
| Uncensored builds | Context | In / out per 1M | 1,000 chat turns |
|---|---|---|---|
| MiniMax M3.1 Flash (Uncensored) | — | $0.045 / $0.18 | $0.18 |
| Llama 3.2 3B Instruct (Uncensored) | — | $0.08 / $0.20 | $0.26 |
| Gemma 3n E2B (Uncensored) | — | $0.12 / $0.08 | $0.28 |
| GLM-5.3 Flash Uncensored | — | $0.1053 / $0.3685 | $0.39 |
| Manta Flash 1.0 (Uncensored) | — | $0.07 / $0.56 | $0.42 |
| Manta Mini 1.0 (Uncensored) | — | $0.07 / $0.56 | $0.42 |
| Muse Spark 1.3 Contributor (Uncensored) | — | $0.15 / $0.30 | $0.45 |
| Gemma 3n E4B (Uncensored) | — | $0.20 / $0.16 | $0.48 |
| Qwen3.6 27B (Uncensored) | — | $0.09 / $0.60 | $0.48 |
| Gemma 4 12B Starry Ocean (Uncensored) | — | $0.175 / $0.875 | $0.79 |
| Gemma 4 12B StationKeeper (Uncensored) | — | $0.175 / $0.875 | $0.79 |
| Magidonia 24B v4.3 (Uncensored) | — | $0.3535 / $0.4235 | $0.92 |
| GLM-5.3 Uncensored | — | $0.282 / $0.846 | $0.99 |
| Step 3.5 Flash (Uncensored) | — | $0.40 / $1.20 | $1.40 |
| Llama 3.3 70B Instruct (Uncensored) | — | $0.40 / $1.28 | $1.44 |
| Qwen3.5 Flash (Uncensored) | — | $0.36 / $1.48 | $1.46 |
Llama 3.3 70B Instruct (Uncensored) 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 llama-3.3-70b-instruct-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 Llama 3.3 70B Instruct (Uncensored) 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 | $1.44 |
| A coding day in OpenCode or Cline | 40 requests of 6,000 input and 1,200 output tokens | $0.1574 |
| One long document, summarised once | 100,000 input and 1,000 output tokens in one request | $0.0413 |
Llama 3.3 70B Instruct (Uncensored) questions
What is Llama 3.3 70B Instruct (Uncensored)?
Llama 3.3 70B Instruct (Uncensored) is an uncensored build of Llama 3.3 70B Instruct from Meta. On PentestLLM it answers as llama-3.3-70b-instruct-uncensored.
Is there a subscription for Llama 3.3 70B Instruct (Uncensored)?
No. Credit is prepaid from $10 and billed per token: input $0.40 and output $1.28 per million tokens, cached input $0.20.
What does a short chat turn on Llama 3.3 70B Instruct (Uncensored) cost?
About $0.001 for 1,000 tokens in and 500 tokens out, at $0.40 in and $1.28 out per million tokens.
Is Llama 3.3 70B Instruct (Uncensored) OpenAI-compatible?
Yes. Send llama-3.3-70b-instruct-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 Llama 3.3 70B Instruct (Uncensored) 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 llama-3.3-70b-instruct-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.
Did Llama 3.3 70B Instruct (Uncensored) pass the daily real-model check?
Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. Llama 3.3 70B Instruct (Uncensored)’s latest result, from Nov 20: steady since Nov 18. See the daily check.
What is Llama 3.3 70B Instruct (Uncensored) based on?
Llama 3.3 70B Instruct (Uncensored) is named for Llama 3.3 70B Instruct, from Meta. No weights, parameter count or training notes are published for this build.
What does Llama 3.3 70B Instruct (Uncensored) cost per 100 messages?
$0.144 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.40 input and $1.28 output per million tokens, from prepaid credit with no subscription.