GEMINI LABJP
OCT 2 — gemini-2.5-flash-image is scheduled to shut down on October 2. It is the original model the world came to know as Nano BananaCAREFUL — The replacement named in the official table, gemini-3.1-flash-image-preview, was itself retired on June 25. The live path is the GA gemini-3.1-flash-imageSEP 30 — gemini-omni-flash-preview shuts down on September 30. Move to gemini-omni-1.1-flash, which went GA on August 27RESOLUTION — gemini-omni-1.1-flash adds a resolution field to video_config, with 360p, 720p, 1080p and 4k to choose fromEARLIEST — Google notes that a shutdown date is the earliest possible date, not a fixed one. No need to panic, but no excuse to wait eitherSAMPLING — temperature, top_p and top_k were deprecated back on July 21. Turning the temperature down is a habit that stops working across generationsOCT 2 — gemini-2.5-flash-image is scheduled to shut down on October 2. It is the original model the world came to know as Nano BananaCAREFUL — The replacement named in the official table, gemini-3.1-flash-image-preview, was itself retired on June 25. The live path is the GA gemini-3.1-flash-imageSEP 30 — gemini-omni-flash-preview shuts down on September 30. Move to gemini-omni-1.1-flash, which went GA on August 27RESOLUTION — gemini-omni-1.1-flash adds a resolution field to video_config, with 360p, 720p, 1080p and 4k to choose fromEARLIEST — Google notes that a shutdown date is the earliest possible date, not a fixed one. No need to panic, but no excuse to wait eitherSAMPLING — temperature, top_p and top_k were deprecated back on July 21. Turning the temperature down is a habit that stops working across generations
TAG

Cost Engineering

1 articles
Back to all tags
Related:
Gemini API1Token Accounting1Agents1Operations1
Gemini API/2026-07-29Advanced

A 17% Drop in Output Tokens Sounded Big. Then I Decomposed the Bill

Output pricing fell 16.67% and output tokens fell about 17%. Adding those numbers does not give you the savings. Here is an exact price/volume/cross-term decomposition, plus a loop measurement where the savings rate went down instead of up.