Google: Gemini Embedding 2 Preview

Coming soonQuick Start

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"}],
)
Wire Gemini Embedding 2 Preview into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free