Gemini Embedding 2
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
Model facts
- Context window
- 8K tokens
- Maximum output
- 3K tokens
- Cheapest paid input
- $0.2 per 1M tokens
- Cheapest paid output
- free per 1M tokens
- Open weights
- no
- Providers
- 3
Capabilities and modalities
attachments, temperature control, text, image, audio, video, pdf.
Observed price history
- 2026-08-24: $0.2 input / free output per 1M tokens
API providers
- Google — model id gemini-embedding-2; $0.2 input / free output per 1M tokens; provider documentation
- SAP AI Core — model id gemini-embedding-2; not published input / not published output per 1M tokens; provider documentation
- Vercel AI Gateway — model id google/gemini-embedding-2; not published input / not published output per 1M tokens; provider documentation