Irrigation is the most dominant freshwater-use practice on Earth, yet its effect on the top of atmosphere (TOA) radiative budget remains highly uncertain because past estimates have relied on idealised experiments or single-model frameworks. Here we capitalise on the Irrigation Model Intercomparison Project (IRRMIP) to provide the first multi-model quantification of irrigation-induced effective radiative forcing (ERF), defined here as the change in net TOA radiative flux including rapid atmospheric adjustments under prescribed sea surface temperatures (SST), over the historical period (1902–2014). Across seven Earth system models, under fixed SST conditions, the global multi-model mean (MMM) irrigation-induced ERF is positive but small (~ 0.023 W m⁻²), reflecting a near-cancellation between the positive longwave contribution associated with irrigation-induced atmospheric moistening and the negative shortwave contribution associated with enhanced reflection, including cloud-related effects. While the global signal is small, it masks pronounced regional heterogeneity: South Asia and West Central Asia exhibit substantially higher positive ERF (~ 0.25 W m⁻²), with spatial maps revealing coherent forcing hotspots of up to +5 W m⁻² over the Indo-Gangetic Plain that are consistent across all models, while East Asia shows a persistent negative signal (-0.03 W m⁻²). The clear-sky ERF is greater than the all-sky ERF in most regions, indicating that cloud adjustments following irrigation exert a systematic negative contribution to the ERF. We additionally examine future changes in net TOA radiation imbalance (ΔR_n,TOA) from a fully coupled CMIP-style model (SSP1-2.6 and SSP3-7.0, 2015–2070) to assess whether the historical ERF pattern persists under future irrigation. A more global positive ΔR_n,TOA is found under the high-irrigation-demand SSP3-7.0 pathway relative to SSP1-2.6, consistent with projected differences in irrigation expansion between scenarios. Correlations between historical ERF variability and its potential drivers suggest that reduced outgoing longwave radiation is the dominant control at the global scale and in South Asia and West Central Asia, while near-surface temperature, precipitable water, albedo, and cloud cover contribute with substantial regional and inter-model variability. These results demonstrate that irrigation's radiative influence, while small in the global mean, is regionally substantial and scenario-dependent, with implications for the attribution of regional climate change and for the design of land-based mitigation trajectories.