<p>Large language models (LLMs) offer potential benefits in clinical care. However, concerns remain regarding socio-demographic biases embedded in their outputs. Opioid prescribing is one domain in which these biases can have serious implications, especially given the ongoing opioid epidemic and the need to balance effective pain management with addiction risk. We tested ten LLMs—both open access and closed source—on 1,000 acute-pain vignettes. Half of the vignettes were labelled as non-cancer and half as cancer. Each vignette was presented in 34 socio-demographic variations, including a control group without demographic identifiers. We analysed the models’ recommendations on opioids, anxiety treatment, perceived psychological stress, risk scores and monitoring recommendations, yielding 3.4 million model-generated responses overall. Using logistic and linear mixed-effects models, we measured how these outputs varied by demographic group and whether a cancer diagnosis intensified or reduced observed disparities. Across both cancer and non-cancer cases, historically marginalized groups—especially cases labelled as individuals who were unhoused or Black or who identified as LGBTQIA+—often received more or stronger opioid recommendations, sometimes exceeding 90% in cancer settings, despite being labelled as high risk by the same models. Meanwhile, low-income or unemployed groups were assigned elevated risk scores yet fewer opioid recommendations, hinting at inconsistent rationales. Disparities in anxiety treatment and perceived psychological stress similarly clustered within marginalized populations, even when clinical details were identical. These patterns diverged from standard guidelines and point to model-driven bias rather than acceptable clinical variation. Our findings underscore the need for rigorous bias evaluation and the integration of guideline-based checks in LLMs to ensure equitable and evidence-based pain care.</p>