ModelRot

gemini-3-flash-preview vs gemini-3.6-flash

Google Gemini names gemini-3.6-flash as the replacement for gemini-3-flash-preview. At standard list prices, gemini-3.6-flash costs +33% per token (blended 3:1 input:output).

Legacy→Active
Per 1M tokensgemini-3-flash-previewgemini-3.6-flash
Input$0.5$0.75
Output$3$3.75
Blended change+33%
ProviderGoogle GeminiGoogle Gemini
Statuslegacyactive
Shutdown——
Context window——

Migrating

  • Replace the ID gemini-3-flash-preview with gemini-3.6-flash everywhere it appears, including .env files, config and infrastructure templates.
  • Run your evaluation set or golden prompts on both before switching: output style, refusals and tool calling can differ between generations.
  • Check max output tokens and parameters: newer models sometimes rename or drop sampling options.
  • Watch the repo on ModelRot so the next retirement doesn't surprise you. gemini-3.6-flash lifecycle.