workhorse

Gemini 2.5 Pro vs Gemini 2.5 Flash

Side-by-side pricing, context window, features, and per-use-case verdict. Data sourced from LiteLLM, updated regularly.

Specifications

Feature Gemini 2.5 Pro Gemini 2.5 Flash
Provider vertex ai-language-models vertex ai-language-models
Model ID gemini-2.5-pro gemini-2.5-flash
Input / 1M tokens $1.25 $0.30 (76% cheaper)
Output / 1M tokens $10.00 $2.50 (75% cheaper)
Cached input / 1M $0.13 $0.03
Context window 1049kk tokens 1049kk tokens
Max output 66kk tokens 66kk tokens
Vision
Function calling
Prompt caching
Web search
JSON schema

Monthly cost comparison

No cache discount applied — pure token costs at three usage scales.

Scale Gemini 2.5 Pro Gemini 2.5 Flash Winner
Small
1M in / 0.2M out
$3.25 $0.80 Gemini 2.5 Flash saves 75%
Medium
10M in / 2M out
$32.50 $8.00 Gemini 2.5 Flash saves 75%
Large
100M in / 20M out
$325 $80.00 Gemini 2.5 Flash saves 75%

Category winners

Cheapest input
Gemini 2.5 Flash
$0.30/M · 76% less than the other
Cheapest output
Gemini 2.5 Flash
$2.50/M · 75% less than the other
Larger context
Gemini 2.5 Pro
1049kk tokens
More features
Gemini 2.5 Pro
5 / 5 capabilities (tied)

Better for…

High-volume RAG & repeated context
$0.03/M cached input — prompt caching makes repeated context retrieval significantly cheaper
Gemini 2.5 Flash
Short interactions & high-throughput APIs
$2.50/M output — 75% cheaper on output at scale
Gemini 2.5 Flash
Cost-sensitive production at scale
$80.00/month at 100M-token scale — 75% cheaper than the alternative
Gemini 2.5 Flash

Deep-dive on each model

Pricing data sourced from LiteLLM and refreshed regularly. Always verify with each provider's official pricing page before making business decisions.