gpt-5-mini vs gemini-2.5-flash

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

Verdict: gpt-5-mini is 20% cheaper on output tokens ($2 vs $2.5 per 1M). Check the context and cached-input rows before deciding on price alone.
gpt-5-minigemini-2.5-flash
Model IDgpt-5-minigemini-2.5-flash
Provideropenaivertex_ai-language-models
Input /1M$0.25$0.3
Output /1M$2$2.5
Cached input /1M$0.025$0.03
Context272,0001,048,576
Max output128,00065,536

gpt-5-mini details · gemini-2.5-flash details