Google/ Gemini
Gemini Embedding 2
google/gemini/embedding-2
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
Released
2026-04-22
Context window
8.2K
Max output
3.1K
Weights
Closed
Modalities
Input
TextImageAudioVideoDocument
Output
Text
Identity
- Version
- gemini-embedding-2
- Knowledge cutoff
- 2025-11
- Aliases
- Gemini Embedding 2
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| gemini-embedding-2 | google_generate_content | 8.2K | 3.1K | TextImageAudioVideoDocument | Text | Attachments | - | input $0.2/M output $0/M | Yes | |
| Vercel AI Gateway | google/gemini-embedding-2 | openai_chat | 8.2K | 3.1K | TextImageAudioVideoDocument | Text | Attachments | - | input $0.2/M | Yes |
Capabilities
Attachments
Official price
input $0.2/M
output $0/M