Skip to content

Compare model prices

Input, output, cached and batch prices, every route and a month of tokens, side by side.

Gemini Embedding 2 PreviewGemini 3.8 Flash

A month of tokens

  • Gemini Embedding 2 Preview$20.00
  • Gemini 3.8 Flash$150.00

100M input and 20M output tokens, list price. Use your own numbers.

Side by side

Gemini Embedding 2 PreviewGemini 3.8 Flash
Input per 1M$0.2$0.75
Output per 1MFree$3.75
Cached inputn/a$0.075
Batch in / outn/a$0.375 / $1.88
Blended (3:1)$0.15$1.5
Context8K1M
Routes16
ReleasedApr 17, 2026Sep 2, 2026
Leadersboard scoren/a15 (#13)

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper

Every route

Gemini Embedding 2 Preview

  • Google Gemini API (list)the lab's own API$0.2 / Free$0.15 blended

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.

Weekly: LLM API list prices that changed, Thursday mornings.