← All models
Google: Gemini Embedding 2
google/gemini-embedding-2embeddings
Google's embedding model: a unified vector space for semantic search and clustering. Through our API the input is text ($0.20/1M tokens); the underlying space is multimodal, but the /v1/embeddings endpoint accepts strings.
Price
Released
May 20, 2026
Parameters
inputa string or array of stringsHow to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
r = client.embeddings.create(
model="google/gemini-embedding-2",
input="Привет! Это Mixen AI.", # строка или список строк
)
vec = r.data[0].embedding
print(len(vec), vec[:3])