Back
GoogleGemini API
Released gemini-embedding-2-preview, our first multimodal embedding model. It supports text, image, video,…
AI summary
Written by AI from the official notes. Check them for exact details.Google released the gemini-embedding-2-preview model, supporting multiple input types. The gemini-2.5-flash-lite-preview-09-2025 model will be deprecated soon.
- Introduced gemini-embedding-2-preview for multimodal inputs.
- Supports text, image, video, audio, and PDF.
- All modalities mapped into a unified embedding space.
- Deprecation of gemini-2.5-flash-lite-preview-09-2025 announced.
Why it matters: Users of AI tools should transition to the new model for enhanced multimodal capabilities.
Full release notes2 changes
- Released
gemini-embedding-2-preview, our first multimodal embedding model. It supports text, image, video, audio, and PDF inputs, mapping all modalities into a unified embedding space. To learn more, see Embeddings. - Deprecation announcement: The
gemini-2.5-flash-lite-preview-09-2025model will be shut down on March 31, 2026.