The translation factor that helps deliver the initiator tRNA to the ribosome, eIF2, uses the energy of GTP hydrolysis for function. Another factor, eIF5, was known to accelerate the GTPase activity of eIF2 when it was bound to the initiator tRNA and the ribosome. In this study two other roles for eIF5 have been defined. One involves stabilizing the binding of GDP, the product of GTP hydrolysis, to eIF2. The other involves its acting with phosphorylated eIF2 to inhibit the guanine nucleotide exchange factor, eIF2B. These results clarify our understanding of how translation initiation is regulated. The initiation of protein synthesis requires the eukaryotic translation initiation factor (eIF) 2, which uses energy from the hydrolysis of GTP. Another factor, eIF5, accelerates the GTP-hydrolysing activity of eIF2. Here, two other roles for eIF5 have been defined. One involves stabilizing GDP, the product of GTP hydrolysis, on eIF2. In its other role, eIF5 works with phosphorylated eIF2 to inhibit the guanine-nucleotide exchange factor eIF2B. These results clarify our understanding of how the initiation of translation is regulated. In protein synthesis initiation, the eukaryotic translation initiation factor (eIF) 2 (a G protein) functions in its GTP-bound state to deliver initiator methionyl-tRNA (tRNAiMet) to the small ribosomal subunit and is necessary for protein synthesis in all cells1,2. Phosphorylation of eIF2 [eIF2(αP)] is critical for translational control in diverse settings including nutrient deprivation, viral infection and memory formation3,4,5. eIF5 functions in start site selection as a GTPase accelerating protein (GAP) for the eIF2·GTP·tRNAiMet ternary complex within the ribosome-bound pre-initiation complex6,7,8. Here we define new regulatory functions of eIF5 in the recycling of eIF2 from its inactive eIF2·GDP state between successive rounds of translation initiation. First we show that eIF5 stabilizes the binding of GDP to eIF2 and is therefore a bi-functional protein that acts as a GDP dissociation inhibitor (GDI). We find that this activity is independent of the GAP function and identify conserved residues within eIF5 that are necessary for this role. Second we show that eIF5 is a critical component of the eIF2(αP) regulatory complex that inhibits the activity of the guanine-nucleotide exchange factor (GEF) eIF2B. Together our studies define a new step in the translation initiation pathway, one that is critical for normal translational controls.