3 Llama builds: 2 abliterated, 1 roleplay.
Every Llama abliterated, uncensored and roleplay build PentestLLM serves, on one key and priced per token. The table lists each build’s price and context window from the live catalog as of 2026-11-18; each name opens its own page with the settings for SillyTavern and Janitor.
Which Llama build to pick
- Largest context
- 32,768 tokens, Aion RP Llama 3.1 8B
- Lowest output price
- $2.80 per million tokens, Llama 3 70B Abliterated v3.5
- Abliterated
- Llama 3 70B Abliterated v3.5, $2.80 per million output tokens
- Roleplay
- Aion RP Llama 3.1 8B, $6.40 per million output tokens
- Prices as of
- 2026-11-18
| Wire formats | |||||
|---|---|---|---|---|---|
| Aion RP Llama 3.1 8B | Roleplay | $3.20 | $6.40 | 33K | |
| Llama 3 70B Abliterated v3.5 | Abliterated | $2.80 | $2.80 | 8K | |
| Llama 3.3 70B Abliterated | Abliterated | $2.80 | $2.80 | 33K |
Llama abliterated vs roleplay builds
- Abliterated
- 2 builds, output from $2.80 per million tokens, context up to 32,768 tokens
- Roleplay
- 1 build, output from $6.40 per million tokens, context up to 32,768 tokens
What the Llama build types mean
- Abliterated (2): a abliterated build is the stock model with its refusal direction removed from the weights. It answers prompts the stock model declines, and there is no jailbreak prompt to keep alive.
- Roleplay (1): a roleplay build is a fine-tune trained on long-form fiction and character dialogue. It holds a character’s voice, follows a scenario and writes at length.
Run Llama abliterated without a GPU
Nothing is downloaded and no card is needed: the builds run on the API. Create a key in the console, set the base URL to https://api.pentestllm.ai/v1, and send the model id from the table as model. Any client that speaks the OpenAI chat format works, from the SDK to SillyTavern and Janitor; the docs page has the setup for each.
Each build is billed to the token from a prepaid balance. The daily real-model check sends a fixed prompt to every model each day and records whether the answer still matches, so the build behind an id is the one on its label.
Llama questions
Yes. PentestLLM lists 2 abliterated Llama builds: Llama 3 70B Abliterated v3.5 and Llama 3.3 70B Abliterated.
2 builds share the largest context window, 32,768 tokens: Aion RP Llama 3.1 8B and Llama 3.3 70B Abliterated.
Output runs from $2.80 to $2.80 per million tokens across the abliterated Llama builds here, with input billed separately at each build’s own rate. There is no subscription: a prepaid balance from $10 pays per token.
Yes. Every build here speaks the OpenAI chat format: point the client at https://api.pentestllm.ai/v1, paste a key and type the model id from the table.
No. An Ollama or GGUF build runs on your own machine and needs the memory for it; these run on the API and are billed per token, so there is nothing to download.