Project AURIONAI Use-Cases Research & Innovation
Google
embeddingfamily

Gemini Embedding

Embedding models built from Gemini for retrieval, classification and clustering via the Gemini API; gemini-embedding-001 is text, Gemini Embedding 2 maps text, images, video, audio and documents into one space.

GoogleGoogleUSA
Figure from the Gemini Embedding paper: Gemini Embedding represents text as dense vectors where semantically similar text inputs are mapped to vectors near one another in the vector space.
Levelfamily
Classembedding
Parametersnot in the notes
Contextnot in the notes
Released10 Mar 2025
Opennessproprietary
Runs onnot in the notes
Statusactive

Lineage

Googlegemini-embedding-001 belongs to this familyembedding10 Mar 2025
GoogleGemini Embedding 2 belongs to this familyembedding
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. Confidence and evidence are the notes' own.

R&D Topics

Retrieval-augmented generation (RAG)used byText embeddings for semantic searchproduced by

Identity

Developer
Google
Family
not in the notes
Released
10 Mar 2025 sourcesannouncement page
Weights published
–
Record checked
12 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
not in the notes
Total parameters
– sources
Active parameters
–
Checkpoint parameters
–
Context length
not in the notes
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
proprietary
Licence
Proprietary sources
Access routes
API
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
not in the notes
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. arxiv.org/abs/2503.07891 https://arxiv.org/abs/2503.07891
  2. ai.google.dev/gemini-api/docs/embeddings https://ai.google.dev/gemini-api/docs/embeddings
  3. docs.cloud.google.com/gemini-enterprise-agent-platform/models/googl... https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/google-models

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Gemini Embedding", https://aurion.semai.id/models/google-gemini-embedding/, records of October 2026.