# Google Gemini 1.5 Pro — deprecation status

> Yes — Gemini 1.5 Pro is retired. Google shut it down on June 17, 2026; API requests to it now fail. The recommended replacement is Gemini 2.5 Pro.

The model that made a million-token context window a mainstream expectation, and for a year the reason teams chose Gemini at all. Google no longer lists it on its deprecations page — rows are removed once a model is long gone — so the shutdown date here comes from the community llm-model-deprecation registry rather than a Google page, and should be treated as less firm than the rest of this site.

## Facts

| Field | Value |
| --- | --- |
| Provider | Google |
| Model id | `gemini-1.5-pro` |
| Status | Retired |
| Aliases | `gemini-1.5-pro-002` |
| Released | February 15, 2024 |
| Shutdown | June 17, 2026 (43 days ago) |
| Last verified | July 30, 2026 |

## Replacement

- **Gemini 2.5 Pro** (`gemini-2.5-pro`) · recommended — https://modeldeprecations.dev/google/gemini-2.5-pro
  - The 2.5 generation thinks before answering by default, which changes both latency and token cost. Budget with thinkingConfig rather than assuming 1.5-era numbers carry over.
  - Parameters it accepts: https://modelparams.dev/models/google/gemini-2.5-pro

```diff
- "model": "gemini-1.5-pro"
+ "model": "gemini-2.5-pro"
```

## FAQ

### When did Google Gemini 1.5 Pro shut down?

Google Gemini 1.5 Pro shut down on June 17, 2026. API requests to it fail from that date onward.

### What replaces Google Gemini 1.5 Pro?

Google recommends Gemini 2.5 Pro (`gemini-2.5-pro`) as the replacement for Google Gemini 1.5 Pro. The 2.5 generation thinks before answering by default, which changes both latency and token cost. Budget with thinkingConfig rather than assuming 1.5-era numbers carry over.

### Is Google Gemini 1.5 Pro still available?

No. Google Gemini 1.5 Pro is retired and no longer served — it was shut down on June 17, 2026. Calls to it return an error.

### How do I migrate from Google Gemini 1.5 Pro to gemini-2.5-pro?

Swap the model id in your API call: replace "gemini-1.5-pro" with "gemini-2.5-pro". The 2.5 generation thinks before answering by default, which changes both latency and token cost. Budget with thinkingConfig rather than assuming 1.5-era numbers carry over.

### Does this apply to gemini-1.5-pro-002 too?

Yes. Google Gemini 1.5 Pro is also published as `gemini-1.5-pro-002`; that id shares the same lifecycle dates as `gemini-1.5-pro`.

## Sources

- [Gemini API deprecations](https://ai.google.dev/gemini-api/docs/deprecations) — accessed 2026-07-30
- [llm-model-deprecation registry (third-party)](https://github.com/techdevsynergy/llm-model-deprecation) — accessed 2026-07-30

---

Canonical page: https://modeldeprecations.dev/google/gemini-1.5-pro
JSON: https://modeldeprecations.dev/api/v1/models/google/gemini-1.5-pro.json