趋近智
参数
未公开
上下文长度
66K
模态
Multimodal
架构
未公开
许可证
专有
发布日期
6 Oct 2026
训练数据截止日期
-
API 价格 (每 1M)
输入: $1.50 · 输出: $7.50
没有可用的 Gemini Nano Banana 2.1 评估基准。
排名
-
编程排名
-
Gemini Nano Banana 2.1 is Google's multimodal image generation and editing model operating on the Flash tier. It offers improved product recontextualization and text-to-image synthesis capabilities.
专有模型的架构规格未公开。
The Gemini Omni family is Google's first generation of native video-generation models, combining Gemini's multimodal reasoning with the ability to create from any input. Announced at Google I/O 2026, Omni models accept combinations of text, images, audio, and video, allowing users to generate and conversationally edit high-quality videos grounded in Gemini's real-world knowledge.
Assistant
在线