Abliterated Large V2 is Abliteration AI's reasoning model derived from Z.ai's GLM-5.3, with refusal behavior removed through abliteration and further fine-tuning. It takes text input and output with a 1M-token context window, always reasons at low, high or max depth, and is aimed at red teaming, security research and agent testing.
Anonymous|1M context|$3.00/M input|$5.00/M output