Learning the food chain in elementary school can be challenging because students need to understand abstract relationships between organisms, including the roles of producers, consumers, and decomposers. This study aimed to develop a 3D animated video based on Artificial Intelligence (AI) with a multimodal approach for teaching food chain concepts in IPAS and to determine its feasibility and learning outcomes. This study employed a Research and Development (R&D) method using the ADDIE development model, consisting of analysis, design, development, implementation, and evaluation stages. The research subjects were 35 fifth-grade students of Class V C at SDN 05 Kota Bengkulu. Data were collected through interviews, observations, material and media expert validation questionnaires, teacher and student response questionnaires, and pretest and posttest assessments. The developed product was a three-minute 3D animated video integrating animated visuals, audio narration, text, and captions to visualize food chain processes in a rice field ecosystem. The validation results showed a feasibility percentage of 92% from the material expert and 94% from the media expert. Teacher and student responses reached 96% and 93.4%, respectively. The mean student score increased from 48.6 in the pretest to 86.3 in the posttest, with an N-Gain score of 0.73, categorized as high. These findings indicate that the developed AI-based 3D animated video has a high level of feasibility, received positive responses from users, and can be used as a supporting learning medium for teaching food chain concepts in elementary school IPAS.