gemini-3.1-flash-lite is not scheduled to shut down sooner than 2027-05-07 per Google Vertex AI's deprecation page (checked 2026-10-17). No official replacement is published on that page. Published on the official docs: input price $0.25 per million tokens, context window 1,048,576 tokens, max output 65,536 tokens.
active
| Announced | Not published |
|---|---|
| Deprecated | Not published |
| Shutdown | Not sooner than 2027-05-07 |
| Kind | not_before |
Release date on the Vertex model versions page: 2026-05-07.
Not published.
See the replacement diff · Google Vertex AI models
| Input price / 1M | $0.25 · source, checked 2026-10-17 |
|---|---|
| Output price / 1M | $1.5 · source, checked 2026-10-17 |
| Cached input / 1M | $0.025 · source, checked 2026-10-17 |
| Context window | 1,048,576 · source, checked 2026-10-17 |
| Max output | 65,536 · source, checked 2026-10-17 |
| Reasoning | Not published |
| Vision | Not published |
| Tools | Not published |
gemini-3.1-flash-lite is not scheduled to shut down sooner than 2027-05-07 per Google Vertex AI's deprecation page (checked 2026-10-17). No official replacement is published on that page. Published on the official docs: input price $0.25 per million tokens, context window 1,048,576 tokens, max output 65,536 tokens.
No official replacement is published on that page.
gemini-3.1-flash-lite status is active.
gemini-3.1-flash-lite | May 7, 2026 | May 7, 2027 or later
Gemini 3.1 Flash-Lite | gemini-3.1-flash-lite | context window 1048576 | maximum output tokens 65536
Gemini 3.1 Flash-Lite Input (text, image, video) $0.25 per 1M tokens for the <= 200K column