Skip to content

Compare models

Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.

Comparison of Gemini 2.5 Flash Preview 05-20 (thinking)
Attribute
gemini-2.5-flash-preview-05-20:thinking
Input$0.075 / 1M
Output$1.75 / 1M
Cache Write (5m)$0.075 / 1M Default rate
Cache Write (1h)$0.075 / 1M Default rate
Cache Read$0.075 / 1M Default rate
Web SearchNo surcharge
Max context1.0M
Max outputUnknown
VisionYes
Function CallingYes
JSON ModeYes
StreamingYes
ProviderGoogle
Categorychat
Charge typePay As You Go
Released—
SummaryGemini 2.5 Flash Preview (May 2025) is Google's high-performance general model built for advanced reasoning, coding, math, and science. It includes built-in “thinking” features to deliver more accurate, context-aware answers.