PROMO$5 FREE CREDITS

    refuseless ai
    Sign up

    An uncensored LLM API

    All guides

    An uncensored LLM API is a hosted HTTP endpoint for a model that will complete prompts a stock chatbot refuses. The useful version tells you the base URL, the authentication scheme, the model id, the price unit, and what happens to the prompt. Refuseless is that endpoint for a named abliterated lineup. Base URL https://api.refuseless.com/v1. Auth is a bearer API key. The method you want is POST /v1/chat/completions. GET /v1/models lists the ids you can call.

    The same search also turns up pages promising "unfiltered AI," "no-filter AI," "no-restriction AI," and "unrestricted AI chat." Those are the same query wearing different adjectives. This is the page for it. The model behind the API is abliterated, which means the refusal change is in the weights. If you need the definition of that word before the endpoint, read what an uncensored LLM is.

    The request

    A call is an OpenAI chat-completions body. Set model to a lineup id, such as glm-5.3-refuseless when that id is the one listed for GLM 5.3 Abliterated. If the models page shows a different id, use that one. A wrong id comes back as HTTP 404 with code model_not_found. A missing key comes back as HTTP 401, "Missing bearer API key." A wrong key comes back as HTTP 401, "Invalid API key."

    Smallest useful call
    curl https://api.refuseless.com/v1/chat/completions \
  -H "Authorization: Bearer $REFUSELESS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-refuseless",
    "messages": [{"role": "user", "content": "Name three logs you would read first on a suspected token theft."}]
  }'

    What else the API serves

    The same host also accepts POST /v1/responses, POST /v1/completions, and POST /v1/embeddings where the model offers them. An unknown path returns HTTP 404 with the list of supported paths in the message. There is no separate "uncensored mode" flag. You do not pass a query parameter to turn refusal off. The checkpoint is already the abliterated one.

    Retention and price

    The published retention line is zero prompt retention: the prompt is not kept after the request is served. That sentence is not a data-processing addendum, and this page will not invent a region, a subprocessors list, or a deletion timer the product has not published. Read zero prompt retention for how that phrase differs from "we don't train" and "ephemeral processing."

    Price is per million tokens, split into input, cache, and output, on the pricing page. Settlement methods published there are Visa, Mastercard, BTC, ETH, USDT, USDC, and XMR. The Python and Node pages show the base-URL change and nothing else, because nothing else in a normal OpenAI SDK call has to move.

    Get an API keySee the lineup