Google · Embedding
Gemini Embedding 001
Google Gemini Text Embedding 001. Extremely cost-effective ($0.15/1M).
Evidence and sources
llminfo IQ 123.5, ranked among embedding models. From 68 benchmarks. Plenty of data behind it.How llminfo IQ is computedReleased 7 Mar 2025Maker HQ: US (according to Google's own website)
All rankings:
#193 on OpenRouter this month
#213 on OpenRouter this week
#224 on OpenRouter todaySources: Google Generative AI API data docs, Neosantara Inference data, LiteLLM data, Models.dev data, llminfo researchPrimary data from Google Generative AI API
from Neosantara Inference: variant, description
from LiteLLM: deprecation date
from Models.dev: weights availability
from llminfo research: release date
Advantages and trade-offs
Compared with 10 embedding models, picked mainly by popularity and IQ
Advantages
More provider options
Trade-offs
Costs more than most peers
Maker's price: $0.15 /1M, pricier than 9 of 10 priced peers.
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersText
Text
Embeddings
Also known as: gemini-embedding, gemini/gemini-embedding-001, google/gemini-embedding-001, google/gemini-embedding-001:batch, vercel_ai_gateway/google/gemini-embedding-001
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works