Gemini Embedding 2 Preview is Google's first multimodal embedding model, released 2026-04. It maps text and images into a unified vector space for semantic search and retrieval-augmented generation, supporting cross-modal similarity so a text query can retrieve the most relevant images or vice versa. Output dimensions are flexible from 128 to 3,072, making it suited to multimodal search, recommendation, and document understanding pipelines.
This model is not routed on MirAPI yet — prices shown are the official list prices. Create an account to get notified when it goes live.
Modalities
inTextinImageinFileinAudioinVideooutVector
Price / 1M
$0.20 / —
Context
8K
Knowledge cutoff
—
Capabilities
VisionStructured output
Quick Start
import os from openai import OpenAI client = OpenAI( base_url="https://api.mirapi.ai/v1", # changed api_key=os.environ["MIRAPI_API_KEY"], # changed ) resp = client.chat.completions.create( model="google/gemini-embedding-2-preview", messages=[{"role": "user", "content": "Hello"}], )
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.mirapi.ai/v1", // changed apiKey: process.env.MIRAPI_API_KEY, // changed }); const res = await client.chat.completions.create({ model: "google/gemini-embedding-2-preview", messages: [{ role: "user", content: "Hello" }], });
curl https://api.mirapi.ai/v1/chat/completions \ -H "Authorization: Bearer $MIRAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "google/gemini-embedding-2-preview", "messages": [{"role": "user", "content": "Hello"}] }'
Links
Wire Gemini Embedding 2 Preview into your product
Start free1M free tokens to start · no card · OpenAI-compatible, one base_url change