# Vertex AI Gemini 2.5 Flash (Vertex AI) — deprecation status

> Yes — Vertex AI deprecated Gemini 2.5 Flash (Vertex AI) and shuts it down on October 20, 2026 (in 39 days). The recommended replacement is Gemini 3.5 Flash-Lite (Vertex AI).

The fast, cheap half of the 2.5 generation on Vertex AI, and the workhorse most workloads defaulted to through late 2025. Google has committed to retiring it on the platform on October 20, 2026, and points users at the 3.x Flash-Lite line as the replacement.

## Facts

| Field | Value |
| --- | --- |
| Provider | Vertex AI |
| Model id | `gemini-2.5-flash` |
| Status | Deprecated |
| Released | June 17, 2025 |
| Shutdown | October 20, 2026 (in 39 days) |
| Last verified | August 21, 2026 |

## Replacement

- **Gemini 3.5 Flash-Lite (Vertex AI)** (`gemini-3.5-flash-lite`) · recommended — https://modeldeprecations.dev/vertex/gemini-3.5-flash-lite
  - Parameters it accepts: https://modelparams.dev/models/vertex/gemini-3.5-flash-lite
- **Gemini 3.1 Flash-Lite (Vertex AI)** (`gemini-3.1-flash-lite`) — https://modeldeprecations.dev/vertex/gemini-3.1-flash-lite
  - Parameters it accepts: https://modelparams.dev/models/vertex/gemini-3.1-flash-lite

```diff
- "model": "gemini-2.5-flash"
+ "model": "gemini-3.5-flash-lite"
```

## FAQ

### When will Vertex AI Gemini 2.5 Flash (Vertex AI) shut down?

Vertex AI Gemini 2.5 Flash (Vertex AI) is scheduled to shut down on October 20, 2026, in 39 days.

### What replaces Vertex AI Gemini 2.5 Flash (Vertex AI)?

Vertex AI recommends Gemini 3.5 Flash-Lite (Vertex AI) (`gemini-3.5-flash-lite`) as the replacement for Vertex AI Gemini 2.5 Flash (Vertex AI).

### Is Vertex AI Gemini 2.5 Flash (Vertex AI) still available?

Yes, for now. Vertex AI Gemini 2.5 Flash (Vertex AI) is deprecated but still answers requests until October 20, 2026. Deprecated models get no further updates and are the first to lose capacity.

### How do I migrate from Vertex AI Gemini 2.5 Flash (Vertex AI) to gemini-3.5-flash-lite?

Swap the model id in your API call: replace "gemini-2.5-flash" with "gemini-3.5-flash-lite". Keep the rest of the request the same, then re-check the parameters the new model accepts before you ship.

## Sources

- [Vertex AI model versions and lifecycle](https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions) — accessed 2026-08-21

---

Canonical page: https://modeldeprecations.dev/vertex/gemini-2.5-flash
JSON: https://modeldeprecations.dev/api/v1/models/vertex/gemini-2.5-flash.json