Gemini 2.5 Flash vs Gemini 3 Flash preview

Gemini 2.5 Flash vs Gemini 3 Flash preview: Gemini 2.5 Flash is cheaper by 40% on average. Gemini 2.5 Flash from Google Vertex AI (1,048,576-token context, reasoning, tool calls) vs. Gemini 3 Flash preview from Google Vertex AI (1,048,576-token context, reasoning, tool calls). Use Agent Command Center to A/B both in shadow mode and pick the winner per workload.

Side-by-side cost

Live workload comparison

Same workload run through both models. The cheaper one is highlighted.

3,000
01,048,576
400
065,535
5,000
01,000,000
Google Vertex AI
$289/mo
Input $0.300/M · Output $2.50/M
Google Vertex AI
$411/mo
Input $0.500/M · Output $3.00/M
At this workload, Gemini 2.5 Flash is 30% cheaper than Gemini 3 Flash preview — a savings of $122/month ($1,461/year).
Production recipe — Agent Command Center
strategy: cost-optimized
primary:
  model: gemini-2-5-flash
  provider: vertex-ai
fallback:
  model: gemini-3-flash-preview
  provider: vertex-ai
shadow: { sample_rate: 0.05 }   # mirror 5% of traffic to compare quality live
Gemini 2.5 Flash Gemini 3 Flash preview
Input price $0.300/M $0.500/M
Output price $2.50/M $3.00/M
Context window 1,048,576 1,048,576
Max output 65,535 65,535
Function calling
Vision
Audio input
Reasoning
Prompt caching
Structured output
Pricing verified May 12, 2026 May 12, 2026
Cheaper option
~40% cheaper than Gemini 3 Flash preview
Larger context
1,048,576 tokens
More capabilities
6 of 6 capability flags advertised

Benchmark comparison

Side-by-side public benchmark scores. Greener bar = winner.

Chatbot Arena ELOgeneral
Gemini 2.5 Flash
1,335
Gemini 3 Flash preview
HumanEvalcode
Gemini 2.5 Flash
87.0%
Gemini 3 Flash preview
MMLU-Proreasoning
Gemini 2.5 Flash
75.0%
Gemini 3 Flash preview
GPQA Diamondreasoning
Gemini 2.5 Flash
68.4%
Gemini 3 Flash preview
AIME 2024math
Gemini 2.5 Flash
60.0%
Gemini 3 Flash preview