All models
gcp_vertex

Gemini Embedding 2

Our cloud
Try in Playground

Gemini Embedding 2 is the first multimodal embedding model in the Gemini API, mapping text, images, video, audio, and documents into one unified embedding space across over 100 languages. Google recommends it for cross-modal semantic search, document retrieval, and recommendation systems. Upgrading from the earlier embedding model requires re-embedding all existing data.

The real Google model

Same weights, same API, same answers. We change only how you pay for it: one key for every maker, one bill, no separate account to open. Every figure on this page comes from Google’s own page — check it.

Maker's own page

Price

per 1M tokens

Input

Output

$0.20

$0.00

Context

8,192

Modalities

Released

Apr 2026

What it would cost you

1000 tokens is roughly 750 English words.

Estimated total$0.40

Where this model runs

gcp_vertex
Google Vertex

Similar models

Models built for the same kind of work, at a similar price.

We do not mark up the price of tokens. It is the same price the provider charges. We earn on the top-up fee.

Use it from your code

Model:gemini-embedding-2
main.py
OpenAI Specification v1.0
from openai import OpenAI

# Works with the official openai package (pip install openai)
client = OpenAI(
    base_url="https://api.flintbeam.com/v1",
    api_key="sk-live-your-api-key"
)

response = client.chat.completions.create(
    model="gemini-embedding-2",
    messages=[
        {"role": "system", "content": "You are an experienced software engineer."},
        {"role": "user", "content": "Describe the architecture of a distributed cache."}
    ],
    temperature=0.7,
    max_tokens=1500
)

print(response.choices[0].message.content)