Purpose <p>To establish a preoperative prediction model for pathological grade of PanNETs based on computed tomography (CT), magnetic resonance imaging (MRI) and endoscopic ultrasonography (EUS).</p> Methods <p>Clinical data of 58 patients with pathologically confirmed PanNETs were included in this retrospectively study and they were divided into grade 1 and grade 2/3. CT, MRI and EUS images were collected within one week before surgery. A clinical predictive model based on the independent clinical risk factors and significant radiological features was established. The area under receiver operating characteristic curve (AUC) was performed to assess the model.</p> Results <p>Gender, pancreatic duct dilatation (PDD) and portal enhancement ratio (PER) were the independent predictors for PanNETs grading (<i>P</i> &lt; 0.05). PanNETs grade 1 and grade 2/3 had statistical difference in elastography score (<i>P =</i> 0.001). The combination of gender, PDD and PER had better predictive efficiency than each of these three predictors alone, with a high AUC of 0.925. The elastography score also achieved an AUC of 0.838.</p> Conclusion <p>We proposed a comprehensive model based on preoperative CT, MRI and EUS to predict grade 1 and grade 2/3 of PanNETs and better informs clinicians on individualized diagnosis and treatment of patients with PanNETs.</p> Graphical Abstract <p></p>