Vertex AI (us-central1-aiplatform.googleapis.com) Gemini 2.0 Flash-Lite model retirement

Stopped workingJune 1, 2026Subscribe to Vertex AI (us-central1-aiplatform.googleapis.com)Share

On June 1, 2026, Vertex AI discontinued Gemini 2.0 Flash-Lite. This retirement affects calls to model Gemini 2.0 Flash-Lite across both model serving and Provisioned Throughput. Calls using this model fail because it is no longer available.

The error you get

What Vertex AI (us-central1-aiplatform.googleapis.com) answers a call to Gemini 2.0 Flash-Lite once the model is gone, as recorded from real responses:

HTTP 404

{"error":{"code":404,"message":"Publisher model `projects/{project}/locations/{region}/publishers/google/models/Gemini 2.0 Flash-Lite` was not found or your project does not have access to it. Ensure you are using a valid model name and that the model is available in the specified region.","status":"NOT_FOUND"}}

What to use instead of Gemini 2.0 Flash-Lite

Use Gemini 3.1 Flash-Lite, Gemma 4, or more recent Gemini releases.

In Vertex AI (us-central1-aiplatform.googleapis.com)'s words

Gemini 2.0 Flash and 2.0 Flash-Lite are discontinued and are no longer available. This includes both model serving and Provisioned Throughput. Use Gemini 3.1 Flash-Lite, Gemma 4, or more recent Gemini releases.

Vertex AI (us-central1-aiplatform.googleapis.com), Changelog

Facts

API: Vertex AI (us-central1-aiplatform.googleapis.com) us-central1-aiplatform.googleapis.com
Model: Gemini 2.0 Flash-Lite
Kind: Model retirement
Announced: June 1, 2026
Takes effect: June 1, 2026
Calls after that day: Fail
Source: Changelog
Last updated: November 2, 2026
Verified: November 3, 2026, against Vertex AI (us-central1-aiplatform.googleapis.com)'s own pages

Questions

When does Gemini 2.0 Flash-Lite shut down?

Calls to the model Gemini 2.0 Flash-Lite on Vertex AI (us-central1-aiplatform.googleapis.com) stopped working on June 1, 2026.

What happens to calls after June 1, 2026?

They have failed since June 1, 2026.

What error does Gemini 2.0 Flash-Lite return once it is shut down?

Vertex AI (us-central1-aiplatform.googleapis.com) answers HTTP 404: "Publisher model `projects/{project}/locations/{region}/publishers/google/models/Gemini 2.0 Flash-Lite` was not found or your project does not have access to it. Ensure you are using a valid model name and that the model is available in the specified region.". Send another model to fix it.

How do I find the calls this hits in my code?

Okapi reads your repository, finds the calls this change hits and opens a pull request with the fix. It never commits to your branches: every change comes as a pull request you review.

More from Vertex AI (us-central1-aiplatform.googleapis.com) 10

Apr 2, 2026 veo-001-preview-0815Model retirement Stopped working
Jun 1, 2026 Gemini 2.0 FlashModel retirement Stopped working
Jun 30, 2026 imagen-3.0-capability-002Model retirement Stopped working
Jun 30, 2026 imagen-4.0-fast-generate-001Model retirement Stopped working
Jun 30, 2026 imagetext@001Model retirement Stopped working
Jul 9, 2026 gemini-2.5-flash-lite-preview-09-2025Model retirement Stopped working
Jul 9, 2026 gemini-2.5-flash-preview-05-2025Model retirement Stopped working
Jul 9, 2026 gemini-3.1-flash-lite-previewModel retirement Stopped working
Jul 17, 2026 gemini-3-pro-image-previewModel retirement Stopped working
Jul 17, 2026 gemini-3.1-flash-image-previewModel retirement Stopped working

You fixed this one by hand.

Okapi opens the pull request with the fix before the next breaking change reaches your code.

Add to GitHub