← Models

Gemini Embedding 2

Google · Gemini Embedding

Google's first multimodal Gemini embedding model, mapping text, images, audio, video, and PDFs into a unified vector space.

Type
embedding
Context
8K tokens
Max Output
N/A
Status
current
Input
$0.2/1M tok
API Access
Yes
License
proprietary
embedding multimodal retrieval vector-search stable
Released March 2026 · Updated June 8, 2026

Overview

Freshness note: Model capabilities, limits, and pricing can change quickly. This profile is a point-in-time snapshot last verified on June 8, 2026.

Gemini Embedding 2 is Google’s first multimodal embedding model in the Gemini line. It maps text, images, audio, video, and PDFs into a single shared vector space, enabling cross-modal retrieval and semantic search without building separate per-modality embedding pipelines. Google’s current model page lists gemini-embedding-2 as stable.

This is the entry to reach for when the question is “how does Google embed multimodal content for retrieval?” rather than “which Google model should I use for chat or reasoning?”

Capabilities

Google’s release and pricing materials highlight a specific capability profile:

  • Multimodal embedding across text, images, audio, video, and PDF inputs into a unified vector space.
  • Direct cross-modal retrieval, including text queries against image, audio, or video corpora without bridging models.
  • Standard embedding-API ergonomics through the Gemini API and Vertex AI.
  • Batch API support at a 50% discount for offline embedding pipelines.
  • Flexible output dimensions from 128 to 3,072, with 768, 1,536, and 3,072 as Google’s recommended sizes.

This is meaningfully different from earlier Gemini embedding models, which were text-only.

Technical Details

Public anchors at this snapshot:

  • Model ID: gemini-embedding-2
  • Multimodal inputs across text, image, audio, video, and PDF
  • Output: dense vector embeddings, not generated tokens
  • Input token limit: 8,192
  • Output dimensions: 128-3,072
  • Available through both the Gemini API for developers and Vertex AI for enterprise

Embedding models do not generate tokens, so maxOutput is set to 0 to reflect that the output is a vector rather than text.

Pricing & Access

Listed Google pricing per 1M tokens for Gemini Embedding 2:

  • Text input: $0.20
  • Image input: $0.45
  • Audio input: $6.50
  • Video input: $12.00
  • Batch API: 50% discount across the listed modalities

Access options:

  • Gemini API for developers
  • Google AI Studio
  • Vertex AI for enterprise customers
  • Compatible with standard Gemini SDK clients

Best Use Cases

Choose Gemini Embedding 2 for:

  • Multimodal retrieval-augmented generation (RAG) that needs to index images, audio, video, or PDFs alongside text.
  • Cross-modal search products where users issue text queries against non-text corpora.
  • Knowledge bases that consolidate document understanding across formats without per-modality embedding pipelines.
  • Teams already running on Gemini, Vertex AI, or Google Cloud who benefit from staying inside one provider.

For pure-text retrieval at lower cost, OpenAI’s text-embedding-3-small remains substantially cheaper. For self-hosted control, open-weight embedding models such as BGE or E5 are still relevant alternatives.

Comparisons

  • OpenAI text-embedding-3-large (OpenAI): Strong text-only embedding model at lower cost per million tokens; Gemini Embedding 2 differentiates on multimodality.
  • OpenAI text-embedding-3-small (OpenAI): Cheap baseline text embeddings; Gemini Embedding 2 is a different product class.
  • Earlier Gemini embedding models (Google): Text-only predecessors; Embedding 2 is the multimodal step change and current recommended migration target.