All model prices

Gemini 3.5 Flash

Vertex AI · gemini-3.5-flash

Gemini 3.5 Flash from Vertex AI: $1.5 per million input tokens, $9 per million output tokens, $0.15 per million cached input tokens. Retires 19 May 2027.

Prices in US dollars per million units
RatePriceApplies
Input$1.5 per 1M input tokensOrdinary
Cached input$0.15 per 1M cached input tokensOrdinary
Output$9 per 1M output tokensOrdinary
Reasoning$9 per 1M reasoning tokensOrdinary
Input$1.5 per 1M input tokensAUDIO
Input$1.65 per 1M input tokensAUDIO, REGIONAL
Input$1.65 per 1M input tokensREGIONAL
Input$0.75 per 1M input tokensBATCH tier
Input$0.825 per 1M input tokensBATCH tier, REGIONAL
Input$0.75 per 1M input tokensFLEX tier
Input$0.825 per 1M input tokensFLEX tier, REGIONAL
Input$2.7 per 1M input tokensPRIORITY tier
Input$2.97 per 1M input tokensPRIORITY tier, REGIONAL
Cached input$0.165 per 1M cached input tokensREGIONAL
Cached input$0.075 per 1M cached input tokensBATCH tier
Cached input$0.083 per 1M cached input tokensBATCH tier, REGIONAL
Cached input$0.075 per 1M cached input tokensFLEX tier
Cached input$0.083 per 1M cached input tokensFLEX tier, REGIONAL
Cached input$0.27 per 1M cached input tokensPRIORITY tier
Cached input$0.297 per 1M cached input tokensPRIORITY tier, REGIONAL
Output$9.9 per 1M output tokensREGIONAL
Output$4.5 per 1M output tokensBATCH tier
Output$4.95 per 1M output tokensBATCH tier, REGIONAL
Output$4.95 per 1M output tokensFLEX tier, REGIONAL
Output$4.5 per 1M output tokensFLEX tier
Output$16.2 per 1M output tokensPRIORITY tier
Output$17.82 per 1M output tokensPRIORITY tier, REGIONAL
Reasoning$9.9 per 1M reasoning tokensREGIONAL
Released
19 May 2026
Retires
19 May 2027
Most input tokens
1,048,576
Most output tokens
65,535