Models / DeepSeek V4.1 Flash 1017 Fast Abliterated

    DeepSeek V4.1 Flash 1017 Fast Abliterated

    DeepSeek V4.1 Flash 1017 Fast Abliterated is an open-weight model with refusal behavior removed from the weights. 1M-token context, $0.12 in and $0.45 out per million tokens.

    curl
    curl https://api.refuseless.com/v1/chat/completions \
      -H "Authorization: Bearer $REFUSELESS_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "deepseek-v4.1-flash-abliterated-fast",
        "messages": [{"role": "user", "content": "Explain what powershell -nop -w hidden -enc does and why defenders flag it."}]
      }'
    Input
    $0.12 per 1M tokens
    Output
    $0.45 per 1M tokens
    Context
    1M tokens
    Speed
    200 tokens per second

    Specifications

    Abliteration finds the direction inside the model that produces refusals and removes it from the weights. The model keeps what the base model knows, and nothing is added to your prompt, so a new session does not bring the refusals back. It can still be wrong, and it does not decide what your use is allowed to be: the terms do. How abliteration works

    Model id
    deepseek-v4.1-flash-abliterated-fast
    Context
    1,048,576 tokens
    Max output
    131,072 tokens
    Input
    $0.12 per 1M tokens
    Cached input
    $0.025 per 1M tokens
    Output
    $0.45 per 1M tokens
    Speed
    About 200 tokens per second
    Weights
    FP8
    Where it runs
    Refuseless servers only. Prompts and outputs are not stored.

    Call it

    Send an OpenAI chat completions request to https://api.refuseless.com/v1 with model set to deepseek-v4.1-flash-abliterated-fast. The Anthropic SDK works too, through /v1/messages. SDK setup

    Try DeepSeek V4.1 Flash 1017 Fast Abliterated

    Create an account, add credit by card or crypto, and call it with your own key. You pay per token.