Autism Spectrum Disorders (ASD) are neurodevelopmental disorders whose diagnosis relies on deficient social interaction and communication together with repetitive behaviours. Multiple studies have highlighted the potential of oxytocin (OT) to ameliorate behavioural abnormalities in animal models and subjects with ASD. Clinical trials, however, yielded disappointing results. Our study aimed at assessing the behavioural effects of different regimens of OT administration in the Oprm1 null mouse model of ASD. We assessed the effects of intranasal OT injected once at different doses (0.15, 0.3, and 0.6 IU) and time points (5, 15, and 30 min) following administration, or chronically, on ASD-related behaviours (social interaction and preference, stereotypies, anxiety, nociception) in Oprm1+/+and Oprm1-/- mice. We then tested whether pairing intranasal OT injection with social experience would influence its outcome on ASD-like symptoms, and measured gene expression in the reward/social circuit. Acute intranasal OT at 0.3 IU improved social behaviour in Oprm1-/- mice 5 min after administration, with limited effects on non-social behaviours. Chronic (8–17 days) OT maintained rescuing effects in Oprm1 null mice but was deleterious in wild-type mice. Finally, improvements in the social behaviour of Oprm1-/- mice were greater and longer lasting when OT was administered in a social context. Under these conditions, the expression of OT and vasopressin receptor genes, as well as marker genes of striatal projection neurons, was suppressed. We detected no sex difference in OT effects. Our results highlight the importance of considering dosage and social context when evaluating the effects of OT treatment in ASD.