Skip to content
modeldeprecations.dev
Calendar Changelog API GitHub

Providers

Anthropic Google OpenAI

Providers

Anthropic 29 Google 24 OpenAI 103
Google gemini-2.5-pro-preview-03-25

Gemini 2.5 Pro (preview 03-25) (Google)

Retired

Yes — Gemini 2.5 Pro (preview 03-25) is retired. Google shut it down on December 2, 2025; API requests to it now fail. The recommended replacement is Gemini 3.1 Pro (preview).

The first 2.5 Pro preview, from March 2025, and the release where Gemini started thinking before answering by default. It was widely benchmarked under this id, which is why it still appears in evaluation code. Shut down December 2025.

The facts

Provider Google
Model id gemini-2.5-pro-preview-03-25
Released March 25, 2025
Deprecated date not published
Shutdown December 2, 2025 · 240 days ago
Status Retired
Last verified July 30, 2026

What to use instead

Google Gemini 3.1 Pro (preview) gemini-3.1-pro-preview Provider-recommended Active

If you are reproducing a benchmark rather than shipping, note that no hosted model reproduces this snapshot's behaviour.

What parameters gemini-3.1-pro-preview accepts on modelparams.dev

Change the id

In most cases the migration is one string. Check the parameter differences before you ship — newer models drop older sampling knobs more often than they add them. 

- "model": "gemini-2.5-pro-preview-03-25"
+ "model": "gemini-3.1-pro-preview"

Frequently asked questions

When did Google Gemini 2.5 Pro (preview 03-25) shut down?
Google Gemini 2.5 Pro (preview 03-25) shut down on December 2, 2025. API requests to it fail from that date onward.
What replaces Google Gemini 2.5 Pro (preview 03-25)?
Google recommends Gemini 3.1 Pro (preview) (`gemini-3.1-pro-preview`) as the replacement for Google Gemini 2.5 Pro (preview 03-25). If you are reproducing a benchmark rather than shipping, note that no hosted model reproduces this snapshot's behaviour.
Is Google Gemini 2.5 Pro (preview 03-25) still available?
No. Google Gemini 2.5 Pro (preview 03-25) is retired and no longer served — it was shut down on December 2, 2025. Calls to it return an error.
How do I migrate from Google Gemini 2.5 Pro (preview 03-25) to gemini-3.1-pro-preview?
Swap the model id in your API call: replace "gemini-2.5-pro-preview-03-25" with "gemini-3.1-pro-preview". If you are reproducing a benchmark rather than shipping, note that no hosted model reproduces this snapshot's behaviour.

Sources

Found something wrong? The data is one YAML file — edit it on GitHub.

This page, for machines

JSON Markdown Badge JSON

Drop the badge in a README so it turns red the day this model is retired:

[![gemini-2.5-pro-preview-03-25](https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/google/gemini-2.5-pro-preview-03-25.json)](https://modeldeprecations.dev/google/gemini-2.5-pro-preview-03-25)

Other Google models

All Google deprecations →

How to use this site

The full guide, in Markdown. Copy it and hand it to a coding agent verbatim.

# How to use modeldeprecations.dev

[modeldeprecations.dev](https://modeldeprecations.dev) answers one question per model: is it deprecated,
when does it shut down, and what replaces it. Every date on the site is cited to the
provider's own documentation, with the date we last checked it.

Three lifecycle states are used, matching the providers' own vocabulary:

- **active** — still supported, no deprecation announced.
- **deprecated** — the provider has announced it is going away. It still answers requests.
- **retired** — API access is gone. Requests fail.

A model can be active *and* carry a shutdown date: Anthropic publishes a
"not sooner than" date and Google publishes an earliest shutdown date for models
that are current and fully supported. Those are reported as scheduled shutdowns,
not deprecations, because that is what the provider actually committed to.

## Check one model

```bash
curl https://modeldeprecations.dev/api/v1/models/openai/gpt-4-32k.json
```

Or fetch the page as Markdown, which includes the answer, the dates and the sources:

```bash
curl https://modeldeprecations.dev/openai/gpt-4-32k.md
```

## Full catalog

```bash
curl https://modeldeprecations.dev/api/v1/models.json
```

Ids are `provider/model`. Dated snapshots (`gpt-4-32k-0613`) are listed as aliases of
their canonical entry rather than as separate records.

Each entry carries `computed_status`, the lifecycle state recomputed against the build
date — so a model whose shutdown has passed reads `retired` without anyone editing data.

## Badges

A shields.io endpoint per model, for READMEs that should go red when a model dies:

```
https://img.shields.io/endpoint?url=https://modeldeprecations.dev/badge/openai/gpt-4-32k.json
```

## Calendar and changelog

- Subscribe to every shutdown date: https://modeldeprecations.dev/calendar.ics
- Changelog RSS: https://modeldeprecations.dev/changelog.xml

## JSON Schema

```bash
curl https://modeldeprecations.dev/api/v1/schema.json
```

## Contribute

Data lives in YAML under `models/{provider}/{model}.yaml` in the
[GitHub repo](https://github.com/mnfst/modeldeprecations.dev). Every lifecycle date needs a source URL; CI rejects a
date without one. Open a PR.

## For agents

- Machine-readable overview: https://modeldeprecations.dev/llms.txt
- This guide plus every model inline: https://modeldeprecations.dev/llms-full.txt
- Any page also exists as Markdown: append `.md` to a model URL.
- In a browser, this site registers a **WebMCP** tool on `navigator.modelContext`:
  `check_model_deprecation`, `list_shutdowns`, `find_replacement`, and `get_usage_guide`.
- Parameters each model accepts are catalogued on the sibling site, https://modelparams.dev.