Compare model

google / Embedding

GoogleGemini Embedding 001

google/gemini-embedding-001

Gemini embeddings (default)

Best for: Semantic search, RAG and clustering

ShareLinkedInX

Catalog status

Enabled

Research checked

2026-10-06

Benchmark results

1 reported results

Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.

1 of 1 results

MTEB (Multilingual)

Retrieval · Vendor-reported

Test conditions and source

This is the GA, stable gemini-embedding-001 model (June 2025), NOT the March 2025 'gemini-embedding-exp-03-07' experimental checkpoint used for the original arXiv paper/early MTEB leaderboard entries — do not conflate the two. Published source text: Google's own Gemini Embedding 2 performance comparison table lists 'gemini-embedding-001 (Legacy text-only Google model)' at 68.4 Mean(Task) on MTEB (Multilingual), distinct from the March 2025 experimental checkpoint.

Tested model: google/gemini-embedding-001

Google DeepMind — Gemini Embedding 2 model page (comparison table) · Checked 2026-10-06

68.4mean task score

Model specifications

Input token limit

2.05K

Published provider limit

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text

Output

Embeddings
Exact model ID
google/gemini-embedding-001
Model type
Embedding
Input token limit
2,048 tokens

Input token limits describe provider input capacity. Published provider limits are not independently tested TokenRex request limits.

Versions and thinking levels

One enabled version is currently listed for this model.

Gemini Embedding 001Selected$0.15 per 1M tokens

Features and tool support

TokenRex’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Input through TokenRex

Available

Text or a list of texts on POST /v1/embeddings.

Output through TokenRex

Available

A number vector for each input, ready for search and matching.

Function tools

Not exposed

Embedding endpoint only — it returns vectors and does not run tools.

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.