Skip to main content
AI News HomeChange Radar

Model provider · Gemini API · Vertex AI

Google model and API lifecycle

Tracks official Gemini API deprecations and release notes plus Vertex AI generative-model lifecycle notices.

3Verified changes
2Upcoming cutoffs
6Affected identifiers
4Official sources

Action required

Upcoming Google deadlines

Complete and regression-test each migration before the provider's announced cutoff.

13 days left

Gemini embedding-2-preview shuts down on August 10, 2026

Move embedding requests to the generally available gemini-embedding-2 model.

Google · Gemini API20 days left

Imagen 4 API models shut down on August 17, 2026

Migrate image-generation workflows to gemini-3.1-flash-image using Google's current image-generation guidance.

Google · Gemini API

Verified July 26, 2026

Published Google lifecycle changes

Exact symptoms and migration actions, linked to the official platform documentation used for verification.

GoogleGemini APIcritical

Gemini embedding-2-preview shuts down on August 10, 2026

Google is shutting down the preview embedding model and lists gemini-embedding-2 as the replacement.

model shutdownChange the model ID to gemini-embedding-2 and validate vector dimensions, storage, and retrieval quality in a staging index before cutover.
GoogleGemini APIcritical

Imagen 4 API models shut down on August 17, 2026

Google is shutting down all three Imagen 4 production model IDs and recommends gemini-3.1-flash-image.

model shutdownMove to gemini-3.1-flash-image and test request shape, output handling, latency, image quality, and safety behavior before the deadline.
GoogleGemini APIhigh

Gemini deprecates temperature, top_p, and top_k

Gemini 3.6 Flash and 3.5 Flash-Lite ignore the sampling parameters; Google says future model generations will return HTTP 400 when they are supplied.

parameter deprecationStrip temperature, top_p, and top_k from Gemini requests and encode response constraints in a clear system instruction.

Official Google source coverage

Change Radar monitors 4 first-party Google documentation pages using a dedicated lifecycle ledger. These are the source pages used to qualify lifecycle records for publication.