Gemini Embedding 2
google/gemini-embedding-2
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
Capabilities
ReasoningNo
Tool callingNo
Structured outputNo
TemperatureFixed
AttachmentYes
Open weightsNo
Limits
Context8,192 tokens
Max inputN/A
Max output3,072 tokens
Details
Familygemini
Knowledge cutoff2025-11
Release date2026-04-22
Last updated2026-04-22
Modalities
Inputtext, image, audio, video, pdf
Outputtext
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A