Using Gemini Embedding 2 on Vercel AI Gateway

Implementation guide · Gemini Embedding · Google DeepMind

Serverless

Vercel AI Gateway exposes Gemini Embedding 2 through model ID google/gemini-embedding-2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-29. Next refresh: weekly.

Quick Start

1
Create an account at Vercel AI Gateway and generate an API key.
2
Use the Vercel AI Gateway SDK or REST API to call google/gemini-embedding-2 — see the documentation for request format.
3
You'll be billed $0.20/1M input. See full pricing.

API Portal Documentation Pricing Model Card

Code Examples

Install

pip install openai

API key

AI_GATEWAY_API_KEY

Model ID

google/gemini-embedding-2

creator/model-name e.g. kwaipilot/kat-coder-pro-v2

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AI_GATEWAY_API_KEY"],
    base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
    model="google/gemini-embedding-2",
    messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)

Pricing on Vercel AI Gateway

Type	Price (per 1M)
Input tokens	$0.20

Capabilities

VisionMultimodalAudio

About Gemini Embedding 2

General availability release of Google's multimodal embedding model, released April 22, 2026. Generates 3072-dimensional vectors from text, images, documents, audio, and video inputs, mapping all modalities into a unified semantic space. Supports custom task instructions to optimize embeddings for retrieval, classification, clustering, or other goals. Output dimensionality is configurable via the output_dimensionality parameter. Priced at $0.20/1M input tokens. Distinct from gemini-embedding-2-preview (the earlier preview version). API ID: gemini-embedding-2.

Full model details →

Model Specs

Released2026-04-22

Vercel