Google: Gemini Embedding 2

Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG).…

google/gemini-embedding-2

Gemini Embedding 2 is Google's first multimodal embedding model. We currently support mapping text and images into a unified vector space for semantic search and retrieval-augmented generation (RAG). It supports input context up to 8,192 tokens and flexible output dimensions from 128 to 3,072 (recommended: 768, 1536, or 3,072). Designed for cross-modal similarity — you can embed a text query and retrieve the most relevant images, or vice versa — making it well-suited for multimodal search, recommendation, and document understanding pipelines.

Specifications & capabilities

Input
text, image, file, audio, video
Output
embeddings
Context window · tokens
8192
Knowledge cutoff
2025-11
Published model ID
gemini-embedding-2@default
Capabilities
audioInput, batch, embeddings, fileInput, multimodal, visionInput
Description source ↗

Evaluations

1–2 / 2

MTEB

62.367%

source id
mteb
leaderboard name
MTEB Overall
dimension
embedding
metric
Average task score
rank
257
sample size
13
aggregation scope
splits
  • test
subsets
  • default
  • english
  • french
  • german
  • spanish
task_count
4
task_names
  • Vidore2BioMedicalLecturesRetrieval
  • Vidore2ESGReportsHLRetrieval
  • Vidore2ESGReportsRetrieval
  • Vidore2EconomicsReportsRetrieval
sample_size
13
subset_count
5
subset_sample
  • default
  • english
  • french
  • german
  • spanish
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 1
source model id
google/gemini-embedding-2
Original result ↗

MTEB

62.367%

source id
mteb
leaderboard name
MTEB Retrieval
dimension
embedding
metric
Average task score
rank
291
sample size
13
aggregation scope
splits
  • test
subsets
  • default
  • english
  • french
  • german
  • spanish
task_count
4
task_names
  • Vidore2BioMedicalLecturesRetrieval
  • Vidore2ESGReportsHLRetrieval
  • Vidore2ESGReportsRetrieval
  • Vidore2EconomicsReportsRetrieval
sample_size
13
subset_count
5
subset_sample
  • default
  • english
  • french
  • german
  • spanish
aggregation_method
mean-of-task-means
model_revision_count
1
model_revision_sample
  • 1
source model id
google/gemini-embedding-2
Original result ↗

Published prices

1–10 / 10

google/gemini-embedding-2 ↗

$6.50

Inference provider
vercelAIGatewayCatalog
Platform
google
Unit
audio_input_tokens_per_million
Currency
USD
Billing conditions
charge
audio_input_token_cost
endpoint
google | google/gemini-embedding-2
model_type
embedding
billing_scope
via Vercel AI Gateway
Billing label
Audio input / 1M tokens
Pricing via
Vercel AI Gateway

google/gemini-embedding-2 ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
google
Unit
input_tokens_per_million
Currency
USD
Billing conditions
endpoint
google | google/gemini-embedding-2
model_type
embedding
billing_scope
via Vercel AI Gateway
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

google/gemini-embedding-2 ↗

$6.50

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
audio_input_tokens_per_million
Currency
USD
Billing conditions
charge
audio_input_token_cost
model_type
embedding
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Audio input / 1M tokens
Pricing via
Vercel AI Gateway

google/gemini-embedding-2 ↗

$0.20

Inference provider
vercelAIGatewayCatalog
Platform
Vercel AI Gateway
Unit
input_tokens_per_million
Currency
USD
Billing conditions
model_type
embedding
quote_scope
gateway_catalog
billing_scope
Vercel public catalog; endpoint prices may differ
Billing label
Input tokens / 1M
Pricing via
Vercel AI Gateway

Provider specifications & access

1–3 / 3

gemini-embedding-2 ↗

source model id
gemini-embedding-2
hosting
gateway
platforms
  • Cheaper Inference
architecture
input_modalities
    output_modalities
    • embeddings
    capabilities

      Gemini Embedding 2 ↗

      source model id
      google/gemini-embedding-2
      hosting
      vercel-gateway
      platforms
      • Vercel AI Gateway
      architecture
      input_modalities
      • text
      output_modalities
      • text
      capabilities
      • embeddings

      Gemini Embedding 2 ↗

      source model id
      publishers/google/models/gemini-embedding-2@default
      hosting
      vertex-managed
      platforms
      • Google Cloud Vertex AI
      max input tokens
      8192
      architecture
      input_modalities
      • audio
      • image
      • text
      • video
      output_modalities
      • embeddings
      capabilities
      • batch
      • multimodal
      • visionInput

      Safety assessments

      1–1 / 1

      Foundation Model Transparency Index 2025 ↗

      41 / 100

      source id
      stanfordFMTI
      canonical model id
      google/gemini-embedding-2
      taxonomy
      transparency
      hazard category
      transparency
      hazard name
      Organization transparency
      policy area
      Google
      assessment type
      organization-level disclosure
      metric
      disclosure_score
      result label
      41 / 100
      sample size
      100
      updated at
      2026-11-09T18:08:05.227Z

      Source specification observations

      1–6 / 6

      openRouter ↗

      field
      context_length
      value
      8192
      normalized value
      8192
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      context_length
      value
      8192
      normalized value
      8192
      scope
      source-model
      source id
      openRouter
      confidence
      1

      vercelAIGatewayCatalog ↗

      field
      knowledge_cutoff
      reported field
      knowledge_cutoff
      value
      2025-11
      normalized value
      2025-11
      precision
      month
      scope
      source-model
      source id
      vercelAIGatewayCatalog
      confidence
      1

      vertexAI ↗

      field
      max_input_tokens
      value
      8192
      normalized value
      8192
      scope
      source-model
      source id
      vertexAI
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      7372
      normalized value
      7372
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      7372
      normalized value
      7372
      scope
      source-model
      source id
      openRouter
      confidence
      1

      Original sources

      1–11 / 11

      Google Cloud · Model page ↗

      OpenRouter · Model page ↗

      OpenRouter · Model page ↗

      Vercel AI Gateway · Model page ↗

      Google Cloud · Documentation ↗

      api.cheaperinference.com · Source snapshot ↗

      GitHub · Catalog ↗

      Google Cloud · Catalog ↗

      Hugging Face · Catalog ↗

      OpenRouter · Catalog ↗

      Vercel AI Gateway · Catalog ↗

      Source links

      1–6 / 6

      Explore more models

      Models

      Loading
      EVIDENCE / COMPARISON

      Benchmarks

      Explore every benchmark

      Loading

      These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

      Install TensorTrace