Skip to content

Google · Embedding

Gemini Embedding 2

Google 🇺🇸EmbeddingGemini familyOne of its sources says the weights aren't publicly available.
From Llmgateway's listing:
Google's recommended embedding model — first multimodal embedding model in the Gemini API (text-only via this endpoint today). Default output dimension 3072; supports the `dimensions` parameter (recommended: 768, 1536, 3072). Embedding space is incompatible with gemini-embedding-001.
llminfo IQ
121.2
Maker's price
$0.20 /1M
Max context
8K
Listings
14

Evidence and sources

llminfo IQ 121.2, ranked among embedding models. From 27 benchmarks. Plenty of data behind it.How llminfo IQ is computedReleased 10 Mar 2026Maker HQ: US (according to Google's own website)
All rankings: #147 on OpenRouter today #170 on OpenRouter this week #182 on OpenRouter this month #255 on OpenRouter today #276 on OpenRouter this week #294 on OpenRouter this monthSources: OpenCode Zen data, Models.dev data, ZenMux data, LLMGateway data, llminfo researchPrimary data from OpenCode Zen from Models.dev: name, weights availability from ZenMux: primary mode from LLMGateway: description from llminfo research: release date

Advantages and trade-offs

Compared with 10 embedding models, picked mainly by popularity and IQ

Advantages

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 5 maker's prices; 6 market median prices.

Input & output

as stated by the model's providers
Text
Images
Audio
Video
Files
Text
Embeddings

Capabilities

Supported operations and provider-stated features

VisionFunction callingPDF inputAudio inputBatch API

Listings

 Googlegemini/gemini-embedding-2-previewSources: LiteLLM data, Models.dev data8K$0.20batch $0.10—$6.50$0.45—
 LlmgatewayInference by Googlegemini-embedding-2Sources: LiteLLM data, LLMGateway dataNot published by the provider$0.20————
 Llmgatewaygemini-embedding-2Sources: LiteLLM data, LLMGateway data8K$0.20————
 NanoGPTgemini-embedding-2-previewSource: NanoGPT8K$0.20————
 Nous Portalgoogle/gemini-embedding-2:batch · batchSource: Nous Portal Inference Gateway data8K$0.10—$3.25—$0.00000023
 Nous Portalgoogle/gemini-embedding-2-previewSources: LiteLLM data, Nous Portal Inference Gateway data8K$0.20—$6.50—$0.00000045
 Zenmuxgoogle/gemini-embedding-2Sources: LiteLLM data, ZenMux data8K$0.20————
 Merge Gatewaygoogle/gemini-embedding-2Sources: LiteLLM data, Models.dev data8K$0.20————
 Venicegemini-embedding-2-previewSource: Venice.ai data2K$0.25————

5 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Embedding

Vision

Around the web

Also known as: gemini embedding 2 preview, gemini-embedding-2-preview, gemini/gemini-embedding-2, gemini/gemini-embedding-2-preview, google/gemini-embedding-2, google/gemini-embedding-2-preview, google/gemini-embedding-2:batch, vertex_ai/gemini-embedding-2, vertex_ai/gemini-embedding-2-preview

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