Google DeepMind (Gemini) / gemini-embedding-2
Gemini Embedding 2 stands out for Unified embeddings for text, images, video, and audio and Cross-modal retrieval in one semantic space. It is best suited to multimodal search and RAG and media similarity and recommendation.
Context
8K
token
Input
$0.18
/ 1M tokens
Output
$0
/ 1M tokens
Quality
—
No score
Overview
Gemini Embedding 2 stands out for Unified embeddings for text, images, video, and audio and Cross-modal retrieval in one semantic space. It is best suited to multimodal search and RAG and media similarity and recommendation.
Multimodal
Accepts text and image input in one request, useful for visual understanding, screenshots, and mixed-context tasks.
Model maker
Google DeepMind (Gemini)
Called through SeaLink's unified account, balance, and OpenAI-compatible API.
Protocol
Embeddings API
Base URL: https://api.sealink.io/v1
Pricing
The final charge follows generated usage and the applicable selector, such as resolution, duration, input type, or provider unit.
API
model
gemini-embedding-2base_url
https://api.sealink.io/v1Auth
Bearer $SEALINK_API_KEYcurl https://api.sealink.io/v1/embeddings \-H "Authorization: Bearer $SEALINK_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "gemini-embedding-2","input": "SeaLink gives you one API for leading AI models."}'
from openai import OpenAIclient = OpenAI(base_url="https://api.sealink.io/v1", api_key="<your-sealink-key>")resp = client.embeddings.create(model="gemini-embedding-2",input="SeaLink gives you one API for leading AI models.",)print(resp.data[0].embedding[:5])
import OpenAI from "openai";const client = new OpenAI({baseURL: "https://api.sealink.io/v1",apiKey: process.env.SEALINK_API_KEY,});const resp = await client.embeddings.create({model: "gemini-embedding-2",input: "SeaLink gives you one API for leading AI models.",});console.log(resp.data[0].embedding.slice(0, 5));