ObjectiveTo explore the current situation of financial toxicity (FT) of breast cancer patients undergoing daytime chemotherapy under the background of diagnosis intervention packet (DIP) and its influencing factors, and to build a risk early warning model.Methods Convenient sampling method was used to select breast cancer patients undergoing chemotherapy in the daytime ward of Tianjin Medical University Cancer Institute & Hospital between April and May 2022. The general data questionnaire and FT comprehensive score scale were used to investigate them, and the influencing factors of patients’ FT were discussed through single factor analysis and logistic regression analysis, and the risk early warning model was established. Hosmer-Lemeshow fitting effect test was used to evaluate the prediction effect of the model.Results A total of 278 patients were included. The median (lower quartile, upper quartile) of FT score was 14.00 (8.75, 23.00), of which 195 patients (70.14%) had FT score≤22; 83 patients (29.86%) had FT scores>22. Logistic regression analysis showed that age, per capita monthly income of families, commercial health insurance, chemotherapy cycle, tumor stage, neoadjuvant chemotherapy were the influencing factors for high-risk FT of breast cancer patients undergoing daytime chemotherapy. The results of Hosmer-Lemeshow goodness of fit test showed that the model-predicted FT of breast cancer patients undergoing daytime chemotherapy was in good agreement with the actual observation value (χ2=10.685, P=0.220). The area under the curve of the model was 0.931 [95% confidence interval (0.900, 0.962)], the sensitivity was 0.807, and the specificity was 0.913.Conclusions The FT of breast cancer patients undergoing daytime chemotherapy is at a high level. Older age, purchase of commercial health insurance, and high per capita monthly income of families are protective factors for high-risk FT. The wind with chemotherapy cycle≤4 weeks, tumor stage Ⅱ, neoadjuvant chemotherapy are high-risk FT risk factors. The final warning model has been tested to have a good prediction effect, which can provide a reference for clinical medical staff to identify high-risk FT patients early and make preventive strategies as soon as possible.