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...
Pricing
Source-reported prices are shown in their native units. No missing fee is estimated.
Input
$0.200
USD / 1M input tokens
Output
Free
USD / 1M output tokens
Image
$0.0000
USD / image unit
Capabilities
A check means the source explicitly lists support; a dash means the source did not publish a value.
Text input Supported
Text output Not listed
Vision Supported
Tools N/A
Reasoning N/A
Structured outputs N/A
Audio Supported
Image generation Not listed
Embeddings Supported
Alternatives
Suggestions use deterministic rules: overlapping modalities, a context window within 2×, and shared source-reported signals. No AI-generated recommendations.
Similar models
Google: Gemini Embedding 2 (batch)
google/gemini-embedding-2:batch
Input
$0.100
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
Google: Gemini Embedding 2 Preview
google/gemini-embedding-2-preview
Input
$0.200
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
hexgrad: Kokoro 82M
hexgrad/kokoro-82m
Input
$0.620
Intelligence
N/A
Similar category, context, price or shared benchmark signals.
Mistral: Codestral Embed 2505
mistralai/codestral-embed-2505
Input
$0.150
Intelligence
N/A
Similar category, context, price or shared benchmark signals.