Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
A month of tokens
Gemini 2.5 Pro$325.00
Gemini 3.8 Flash$150.00
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| Gemini 2.5 Pro | Gemini 3.8 Flash | |
|---|---|---|
| Input per 1M | $1.25 | $0.75 |
| Output per 1M | $10 | $3.75 |
| Cached input | $0.125 | $0.075 |
| Batch in / out | $0.625 / $5 | $0.375 / $1.88 |
| Blended (3:1) | $3.44 | $1.5 |
| Context | 1M | 1M |
| Routes | 8 | 6 |
| Released | Jun 17, 2025 | Sep 2, 2026 |
| Leadersboard score | n/a | 15 (#13) |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
Gemini 2.5 Pro
Google Gemini APIflex-50%$0.625 / $5cached $0.063
Google Vertex AIeu$1.25 / $10cached $0.125
Google Vertex AIglobal$1.25 / $10cached $0.125
Google Vertex AIus$1.25 / $10cached $0.125
Google Gemini API (list)the lab's own API$1.25 / $10cached $0.125
OCI Generative AIdefault region, $1.25 / $10 per 1,000,000 tokens$1.25 / $10$3.44 blended
Google Vertex AIglobal-priority+80%$2.25 / $18cached $0.225
Google Gemini APIpriority+80%$2.25 / $18cached $0.225
Gemini 3.8 Flash
Google Vertex AIglobal-flex-50%$0.375 / $1.88cached $0.037
Google Gemini APIflex-50%$0.375 / $1.88cached $0.037
Google Vertex AIglobal$0.75 / $3.75cached $0.075
Google Gemini API (list)the lab's own API$0.75 / $3.75cached $0.075
Google Vertex AIglobal-priority+80%$1.35 / $6.75cached $0.135
Google Gemini APIpriority+80%$1.35 / $6.75cached $0.135
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.