gemini-2.5-pro vs gemini-2.5-flash

Same spec sheet, same units: prices per 1M tokens, updated 2026-11-20.

Verdict: gemini-2.5-flash is 75% cheaper on output tokens ($2.5 vs $10 per 1M). Check the context and cached-input rows before deciding on price alone.
gemini-2.5-progemini-2.5-flash
Model IDgemini-2.5-progemini-2.5-flash
Providervertex_ai-language-modelsvertex_ai-language-models
Input /1M$1.25$0.3
Output /1M$10$2.5
Cached input /1M$0.125$0.03
Context1,048,5761,048,576
Max output65,53665,536

gemini-2.5-pro details · gemini-2.5-flash details