Gemini 3.5 Flash
No shutdown before this date. Gemini 3.5 Flash stays on Google Vertex AI until at least May 19, 2027. Google names Gemini 3.6 Flash as the replacement.
≥ 7 mo- Earliest retirement
- ≥ 217 daysMay 19, 2027 · Google Vertex AI
- Arena Text
- 1,478#18 of 128 · Arena
- GPQA Diamond
- 92.8%#18 of 108 · Epoch AI
- Context window
- 1MMax output 65.5K tokens
- Released
- May 19, 2026Google
Dates on every platform
| Platform | Model ID and status | Deprecated | Shuts down | Replacement |
|---|---|---|---|---|
| Gemini APIGoogle: Gemini API release notes (opens in a new tab) · checked Oct 14, 2026 | gemini-3.5-flashLegacy | None set | Gemini 3.6 Flash | |
| Google Vertex AIGoogle Cloud: Model versions and lifecycle (opens in a new tab) · checked Oct 14, 2026 | gemini-3.5-flashActive | – | ≥ 7 moNot sooner than | – |
Deprecated on October 8, 2026. Requests to this ID are served by Gemini 3.6 Flash; the endpoint is not shutting down.
Still served here; the Gemini API routes this ID to Gemini 3.6 Flash.
Since Oct 8, 2026, requests to gemini-3.5-flash on Gemini API are answered by Gemini 3.6 Flash, with no error. Behavior and price follow the newer model.
What breaks when you move off Gemini 3.5 Flash
Intelligence
| Benchmark | Publisher | Score | Rank | Published |
|---|---|---|---|---|
| Arena Text | Arena | 1,478 ± 2 | #18 of 128 | Oct 8, 2026 |
| GPQA Diamond | Epoch AI | 92.8% ± 1.6% | #18 of 108 | May 22, 2026 |
| Arena WebDev | Arena | 1,499 ± 4 | #32 of 69 | Oct 8, 2026 |
| FrontierMath Tier 4 | Epoch AI | 26.8% ± 7.0% | #34 of 58 | Jun 10, 2026 |
| FrontierMath Tiers 1-3 | Epoch AI | 62.8% ± 2.9% | #33 of 71 | Jun 10, 2026 |
| OTIS Mock AIME 2024-2025 | Epoch AI | 95.6% ± 2.7% | #30 of 105 | May 25, 2026 |
| SimpleQA Verified | Epoch AI | 66.2% ± 1.5% | #12 of 68 | Aug 27, 2026 |
| SWE-bench Verified | Epoch AI | 79.3% ± 1.8% | #2 of 28 | Jun 1, 2026 |
Arena (arena.ai), https://arena.ai/leaderboard
Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource].
List prices
| Platform | Input | Cached | Output | In effect | Source |
|---|---|---|---|---|---|
Google Vertex AIgemini-3.5-flash | $1.50 | $0.15 | $9.00 | May 19, 2026Current · Global endpoint price; regional endpoints cost more. | Google Cloud: Agent Platform pricing (opens in a new tab) |
Change history
RedirectGemini 3.5 Flash requests now go to Gemini 3.6 FlashGemini API1 break
Google deprecated gemini-3.5-flash on the Gemini API and routes its requests to gemini-3.6-flash without an error. Responses now come from a different model.
- Platform
- Gemini API
- Model
- Gemini 3.5 Flash
- Replacement
- Gemini 3.6 Flash
- Announced
- ParametersGemini 3.6 Flash ignores temperature, top_p and top_k, and returns a 400 error when the last turn is a prefilled model turn.
Source: Google, Gemini API release notes (opens in a new tab); Google, Gemini deprecations (opens in a new tab); Google, What's new in Gemini 3.6 Flash and 3.5 Flash-Lite (opens in a new tab)