Abliterated models

An abliterated model is an open-weight LLM with the refusal direction removed from its weights, so it answers instead of declining. Wild West API sells abliterated and uncensored AI models on one OpenAI-compatible endpoint, priced per token with a hard cap on every key.

What abliteration actually does

A language model's tendency to refuse is not spread evenly through the weights. It concentrates in a single direction in the residual stream, and that direction can be found by running the model over a batch of harmful prompts and a batch of harmless ones and taking the mean difference of the activations at the last token.

Abliteration projects that direction out of the embedding matrix, every attention output projection and every MLP output projection. What is left cannot represent refusal, so it does not refuse. No retraining, no fine-tuning data, no prompt engineering: it is surgery on the weights, and it survives whatever you put in the context window. The method step by step is in the abliteration explainer.

Abliterated and uncensored models you can call

Every model below is on sale today, at the price shown per million tokens. The abliterated tag comes straight from the API's own abliterated field; the rest of the line is uncensored: builds with the refusal training taken off, which refuse far less than the stock model but were not edited along the refusal direction.

Who publishes abliterated models

Most abliterated weights are community releases on Hugging Face rather than hosted products. FailSpy published the first ones and named the technique. Maxime Labonne (mlabonne) wrote the tutorial most people learned it from, and released NeuralDaredevil 8B Abliterated, an abliteration followed by a DPO retune to win back what the edit cost. huihui-ai has since published abliterated versions of most major open models. abliteration.ai is the company that sells its own abliterated models as a hosted API.

Wild West API does not resell any of those. It sells the line above, and where a model people search for has no equivalent on it, the page for that model says so and names the nearest one: abliteration.ai's Abliterated Model Large V2, for example, or the uncensored AI pages for GLM, Kimi, DeepSeek, MiniMax and the rest.

Calling one

Anything that speaks the OpenAI chat completions format works unchanged. Point it at Wild West API, use your key, and name the model. The same models answer on the Anthropic Messages format too, so Claude Code drives them directly.

curl https://wildwestapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-ww-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2.6-flash-xploded",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://wildwestapi.com/v1",
    api_key="sk-ww-...",
)
resp = client.chat.completions.create(
    model="mimo-v2.6-flash-xploded",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

Read further

• How abliteration strips the refusals out
• Uncensored or abliterated?
• What abliteration costs a model
• Best uncensored LLM for roleplay
• SillyTavern setup