Context : Aims : Clusters of stars are key objects for the study of the dynamical and chemical evolution of the Galaxy and its neighbors . In particular chemical composition is obtained from different kinds of stars ( hot main-sequence stars , cool main-sequence stars , horizontal-branch stars , RGB stars ) using different methodologies . Our aim is to apply these methodologies to the stars of the Open Cluster NGC 6475 . Obtaining a census of the most important elements we will be able to test their consistence . We finally want to establish more robust fundamental parameters for this cluster . Methods : We selected high S/N high resolution spectra of 7 stars of the Open Cluster NGC 6475 from the ESO database covering the T _ { eff } range 4500-10000 K and of luminosity class V ( dwarf ) and III ( giants ) . We determined the chemical abundances of several elements . For hot stars ( T _ { eff } > 9000 K ) we applied the Balmer Lines fitting method to obtained atmospheric parameters . For cool stars ( T _ { eff } < 6500 K ) we used the FeI/II abundance equilibrium method . For the two groups of stars the use of different line-lists was mandatory . LTE approximation was used . For elements affected by NLTE deviation ( C , N , O , Na , Mg ) corrections were applied . The abundance of many elements were obtained from the measurement of the equivalent width of spectral lines . For those elements for which only blended lines were available ( O , He ) comparison of real spectrum with synthetic ones was used . Hyperfine structure was taken in account for V and Ba . Results : First of all we showed that the two methodologies we used give abundances which are in agreement within the errors . This implies that no appreciable relative systematic effects are present for the derived chemical content of cool and hot stars . On the other hand giants stars show clear chemical peculiarities with respect the dwarf concerning light elements ( up to Si ) and maybe Ba . This fact can be explained as an evolutionary effect . Then , having a new estimation of the metallicity for the cluster ( [ Fe/H ] =+0.03 \pm 0.02 , [ \alpha /Fe ] =-0.06 \pm 0.02 ) we fitted suitable isochrones to the CMD of the cluster obtaining the basic parameters ( E ( B-V ) =0.08 \pm 0.02 , ( m-M ) _ { 0 } =7.65 \pm 0.05 , Age=200 \pm 50 ) . Conclusions :