This　paper　introduces　a　predictive　congestion　pricing　method　in　cities　wherein　the　tolls　alter　from　region　to　region.　We　consider　a　large　urban　network　is　partitioned　into　multiple　regions　each　with　a　well-defined　Macroscopic　Fundamental　Diagram　(MFD)　where　multiple　routes　exist　between　each　origin　and　destination　regions.　The　proposed　cordon　pricing　method　is　designed　to　(i)　minimize　vehicles＇　total　time　spent　in　the　network　and　(ii)　aim　for　a　revenue-neutral　tolling.　A　controller　based　on　model　predictive　control　(MPC)　approach　is　proposed　to　determine　the　(possibly　negative)　optimal　time-and　region-varying　tolls.　The　MPC　controller　comprises　a　regional　MFD-based　traffic　model　with　no　need　of　destination　information　and　a　long-short　term　memory　neural　network　(LSTM-NN)　to　obtain　an　accurate　estimation　of　inter-region　transfer　flows.　Results　of　numerical　experiments　indicate　the　effectiveness　of　the　proposed　congestion　pricing　method　to　achieve　the　two　objectives　simultaneously,　compared　with　No　toll　and　reactive　feedback　controllers.