Abstract The plant‐based dietary indices (PDIs), which include the healthy and unhealthy plant‐based dietary indices, have recently been developed by taking into account the quantity of plant versus animal foods and the quality of plant foods. Data on the association between PDI and hepatocellular carcinoma (HCC) risk are sparse. We, therefore, prospectively evaluated the associations for PDI, healthy PDI (hPDI) and unhealthy PDI (uPDI) with HCC risk. We used data from the Singapore Chinese Health Study, a prospective cohort study of 63,275 participants aged 45–74 in Singapore who were recruited during the 1993–1998 period. PDI, hPDI, and uPDI were derived from the semi‐quantitative food frequency questionnaire at baseline. The incident cases of HCC were identified through record linkage with the Singapore Cancer Registry. Cox proportional hazard regression method was used to calculate hazard ratios (HRs) and 95% confidence intervals (CIs) for HCC in relation to PDI, hPDI, and uPDI. After 17.6 years of follow‐up with 819,573 person‐years, we identified 561 incident HCC cases. There was an inverse association for HCC risk with PDI (HR per‐SD increment = 0.87, 95% CI: 0.79–0.95; P trend = 0.009) and hPDI (HR per‐SD increment = 0.86, 95% CI: 0.79–0.94; P trend = 0.002). This inverse association was similar for HBsAg‐negative and HBsAg‐positive HCC risk. No association was found between uPDI and HCC risk. In summary, the overall PDI and hPDI were associated with lower risk of HCC in the Chinese Singaporeans. Our findings inform dietary targets for HCC prevention and control programs, particularly in Asian populations.