6月 🎉 GPT 85 折 🎉 直降 15% 全系列生效 🔥查看详情
Gemini

Google: Gemini Embedding 2 Preview

Embedding
google/gemini-embedding-2-preview

Gemini Embeddings is a multimodal embedding technique that converts text, audio, video, and image data into numerical vectors that can be processed by machine learning algorithms, especially large models. These vector representations are designed to capture the semantic meaning and context of the data they represent.

上下文窗口
8K
最大输出 Token
8K
发布日期
2026-03-10
能力
视觉音频输入视频输入
可用供应商
GoogleCloudVertex
支持的协议
Geminigemini

供应商

GoogleCloudVertex
输入 Token
$0.2/M
输出 Token
$0/M
图像输入
$0.45/M
音频输入
$6.5/M
视频输入
$12/M
接入协议
Geminigemini

代码示例

from google import genai
client = genai.Client(
api_key="YOUR_OFOX_API_KEY",
http_options={"api_version": "v1beta", "base_url": "https://api.ofox.ai/gemini"},
)
response = client.models.embed_content(
model="google/gemini-embedding-2-preview",
contents="Hello, world!",
)
print(response.embeddings[0].values[:5])

常见问题

Google: Gemini Embedding 2 Preview 在 Ofox.ai 上的价格为输入 $0.2/M/百万 Token,输出 $0/百万 Token。按量计费,无月费。