Gemini Embedding 2
gemini-embedding-2
ProprietaryMultimodal
About
General availability release of Google's multimodal embedding model, released April 22, 2026. Generates 3072-dimensional vectors from text, images, documents, audio, and video inputs, mapping all modalities into a unified semantic space. Supports custom task instructions to optimize embeddings for retrieval, classification, clustering, or other goals. Output dimensionality is configurable via the output_dimensionality parameter. Priced at $0.20/1M input tokens. Distinct from gemini-embedding-2-preview (the earlier preview version). API ID: gemini-embedding-2.
Gemini Embedding 2 input tokens at $0.2/1M, output at $0/1M.
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudioFine-tuning
Providers(1)
| Provider | Input (per 1M) | Output (per 1M) | Type | |
|---|---|---|---|---|
| Google AI Studio | $0.2 | $0 | Serverless |
Rankings
Specifications
FamilyGemini Embedding
Released2026-04-22
Specializationembedding
LicenseProprietary
Trainingpretrained
