# Google AI Studio 弃用 Gemini 2.5 Pro 与 2.5 Flash,API 请求将于 12 月 1 日起自动路由
> 原标题:November 2, 2026
- 来源:Gemini API:更新日志
- 发布时间:2026-11-02T00:00:00.000Z
- AIHOT:https://aihot.news/items/ewvepczpb5fewcbzo2tkqdldm
- 原文:https://ai.google.dev/gemini-api/docs/changelog#11-02-2026
## 摘要
Gemini 2.5 Pro 与 Gemini 2.5 Flash 已弃用,无法再在 Google AI Studio 中选择。
## 推荐理由
原文明确了弃用时间、自动路由目标和计费规则,以及破坏性 API 变更点,方便开发者提前迁移。
## 正文 · 中文译文
- **Gemini 2.5 Pro 弃用**: [`gemini-2.5-pro`](https://aistudio.google.com/docs/models/gemini-2.5-pro) 已[弃用](https://aistudio.google.com/docs/deprecations#gemini-2.5-pro-models),在 Google AI Studio 中已无法选择。自 2026 年 12 月 1 日起,所有发往 `gemini-2.5-pro` 的 API 请求将自动路由至 [`gemini-3.8-flash`](https://aistudio.google.com/docs/models/gemini-3.8-flash),并按 [Gemini 3.8 Flash 费率](https://aistudio.google.com/docs/pricing#gemini-3.8-flash)计费。请在 2026 年 12 月 1 日前将模型字符串更新为 `gemini-3.8-flash`,并查阅 [Gemini 3.8 Flash 迁移指南](https://aistudio.google.com/docs/whats-new-gemini-3.8#migrate-to-gemini-3-8-flash)。 API 的破坏性变更包括:函数调用与 `thought_signature` 校验、`thinking_level` 取代 `thinking_budget`,以及移除采样参数和预填充模型轮次。
- **Gemini 2.5 Flash 弃用**: [`gemini-2.5-flash`](https://aistudio.google.com/docs/models/gemini-2.5-flash) 已[弃用](https://aistudio.google.com/docs/deprecations#gemini-2.5-flash-models),在 Google AI Studio 中已无法选择。自 2026 年 12 月 1 日起,所有发往 `gemini-2.5-flash` 的 API 请求将自动路由至 [`gemini-3.5-flash-lite`](https://aistudio.google.com/docs/models/gemini-3.5-flash-lite),并按 [Gemini 3.5 Flash-Lite 费率](https://aistudio.google.com/docs/pricing#gemini-3.5-flash-lite)计费。 请在 2026 年 12 月 1 日前将模型字符串更新为 `gemini-3.5-flash-lite`,并查阅 [Gemini 3.5 Flash-Lite 迁移指南](https://aistudio.google.com/docs/whats-new-gemini-3.6#migrate-to-gemini-3-5-flash-lite)。 API 的破坏性变更包括:函数调用与 `thought_signature` 校验、`thinking_level` 取代 `thinking_budget`,以及移除采样参数和预填充模型轮次。
## 正文 · 原文
- **Gemini 2.5 Pro deprecation**: [`gemini-2.5-pro`](https://aistudio.google.com/docs/models/gemini-2.5-pro) is [deprecated](https://aistudio.google.com/docs/deprecations#gemini-2.5-pro-models) and is no longer available to select in Google AI Studio. Effective December 1, 2026, all API requests to `gemini-2.5-pro` will automatically route to [`gemini-3.8-flash`](https://aistudio.google.com/docs/models/gemini-3.8-flash) and be billed at [Gemini 3.8 Flash rates](https://aistudio.google.com/docs/pricing#gemini-3.8-flash). Before December 1, 2026, update your model string to `gemini-3.8-flash` and review the [Gemini 3.8 Flash migration guide](https://aistudio.google.com/docs/whats-new-gemini-3.8#migrate-to-gemini-3-8-flash). Breaking API changes include function calling and `thought_signature` validation, `thinking_level` replacing `thinking_budget`, and removed sampling parameters and prefilled model turns.
- **Gemini 2.5 Flash deprecation**: [`gemini-2.5-flash`](https://aistudio.google.com/docs/models/gemini-2.5-flash) is [deprecated](https://aistudio.google.com/docs/deprecations#gemini-2.5-flash-models) and is no longer available to select in Google AI Studio. Effective December 1, 2026, all API requests to `gemini-2.5-flash` will automatically route to [`gemini-3.5-flash-lite`](https://aistudio.google.com/docs/models/gemini-3.5-flash-lite) and be billed at [Gemini 3.5 Flash-Lite rates](https://aistudio.google.com/docs/pricing#gemini-3.5-flash-lite). Before December 1, 2026, update your model string to `gemini-3.5-flash-lite` and review the [Gemini 3.5 Flash-Lite migration guide](https://aistudio.google.com/docs/whats-new-gemini-3.6#migrate-to-gemini-3-5-flash-lite). Breaking API changes include function calling and `thought_signature` validation, `thinking_level` replacing `thinking_budget`, and removed sampling parameters and prefilled model turns.