AI Gateway adds unified fast mode support

T1Covered by 1 source · first reported by Vercel (blog + changelog) at 31 Jul, 00:00 UTC

AI Gateway has a unified fast mode abstraction, now in beta. fast mode fast You can now requestthe same way for every model on AI Gateway. Set speed to, and the gateway serves the fast tier when it's available and falls back to standard speed when it isn't. Fast mode trades a higher per-token cost…

Sources

• T1AI Gateway adds unified fast mode supportVercel (blog + changelog)31 Jul, 00:00