All model prices

Gemini 3.1 Flash Lite

Vertex AI · gemini-3.1-flash-lite

Gemini 3.1 Flash Lite from Vertex AI: $0.25 per million input tokens, $1.5 per million output tokens, $0.025 per million cached input tokens. Retires 7 May 2027.

Prices in US dollars per million units
RatePriceApplies
Input$0.25 per 1M input tokensOrdinary
Cached input$0.025 per 1M cached input tokensOrdinary
Output$1.5 per 1M output tokensOrdinary
Reasoning$1.5 per 1M reasoning tokensOrdinary
Input$0.5 per 1M input tokensAUDIO
Input$0.275 per 1M input tokensREGIONAL
Input$0.55 per 1M input tokensAUDIO, REGIONAL
Input$0.138 per 1M input tokensBATCH tier, REGIONAL
Input$0.125 per 1M input tokensBATCH tier
Input$0.138 per 1M input tokensFLEX tier, REGIONAL
Input$0.125 per 1M input tokensFLEX tier
Input$0.45 per 1M input tokensPRIORITY tier
Input$0.495 per 1M input tokensPRIORITY tier, REGIONAL
Cached input$0.028 per 1M cached input tokensREGIONAL
Cached input$0.014 per 1M cached input tokensBATCH tier, REGIONAL
Cached input$0.013 per 1M cached input tokensBATCH tier
Cached input$0.014 per 1M cached input tokensFLEX tier, REGIONAL
Cached input$0.013 per 1M cached input tokensFLEX tier
Cached input$0.045 per 1M cached input tokensPRIORITY tier
Cached input$0.05 per 1M cached input tokensPRIORITY tier, REGIONAL
Output$1.65 per 1M output tokensREGIONAL
Output$0.825 per 1M output tokensBATCH tier, REGIONAL
Output$0.75 per 1M output tokensBATCH tier
Output$0.825 per 1M output tokensFLEX tier, REGIONAL
Output$0.75 per 1M output tokensFLEX tier
Output$2.7 per 1M output tokensPRIORITY tier
Output$2.97 per 1M output tokensPRIORITY tier, REGIONAL
Reasoning$1.65 per 1M reasoning tokensREGIONAL
Released
7 May 2026
Retires
7 May 2027
Most input tokens
1,048,576
Most output tokens
65,536