Compare model

google / Embedding

Gemini Embedding 001

google/gemini-embedding-001

Gemini embeddings (default)

Catalog status

Enabled

Research checked

2026-10-06

Benchmark results

1 reported results

Results are source-attributed, not TokenBazaar 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 TokenBazaar request limits.

Versions and thinking levels

One enabled version is currently listed for this model.

Gemini Embedding 001Selected₹7.20 per 1M tokens

Features and tool support

TokenBazaar’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 TokenBazaar

Not verified

Consult the integration documentation; no additional input formats are claimed here.

Output through TokenBazaar

Not verified

Output compatibility has not been independently verified for this exact model.

Function-tool conversations

Not exposed

This is a dedicated media or utility endpoint, not a conversational function-tool interface.

Sources and verification

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