Gemini 2.5 Pro vs Gemini 3 Flash Preview: cost compared

Last verified

Gemini 3 Flash Preview is 60% cheaper on input and 70% cheaper on output than Gemini 2.5 Pro. Whether that makes it the right choice depends entirely on whether it does your task well enough — this page gives you the cost side of that trade, precisely.

Rates side by side

$ per million tokensGemini 2.5 ProGemini 3 Flash Preview
Input$1.25$0.50
Output$10.00$3.00
Cached input$0.13$0.05
Output : input ratio8.0×6.0×

What the difference is worth

Monthly cost for the same workload on each, without caching:

WorkloadGemini 2.5 ProGemini 3 Flash PreviewDifference
Support chatbot
1,000 conversations/month · 2,000 in + 500 out each
$7.50$2.50$5.00 saved
RAG search
10,000 queries/month · 8,000 in + 400 out each
$140$52.00$88.00 saved
Bulk extraction
10,000 documents · 3,000 in + 300 out each
$67.50$24.00$43.50 saved
Coding agent
100 runs/month · 400,000 in + 20,000 out each
$70.00$26.00$44.00 saved

Which to use

Gemini 3 Flash Preview if the task is well-specified and mechanical — extraction, classification, formatting, routine transformation. The saving is real and compounds with volume.

Gemini 2.5 Pro if the task involves genuine reasoning, long-horizon planning, or work where a wrong answer is expensive to catch. Paying 2.5× more on input is trivial compared to the cost of shipping a bad result.

Both are Google models, so switching is usually a one-line change and the tokenizer is the same — which makes this a genuinely easy experiment to run. Test on your own workload before deciding.

Don't skip caching

Cached input costs $0.13 on Gemini 2.5 Pro and $0.05 on Gemini 3 Flash Preview. If your prompts share a stable prefix, caching on the more expensive model can beat switching to the cheaper one outright — worth checking before you migrate anything.

Sources

Google rates verified 2026-08-05 (source). Google rates verified 2026-08-05 (source).