Google DeepMind
Gemini Embedding 2 Preview
Image inputAudio inputVideo inputFile input
- Context
- 8K
- Released
- 7mo ago
- Input / 1M tokens
- $0.20
- Output / 1M tokens
- $0.00
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- Google DeepMind
- Model family
- Gemini
- Type
- Embedding
- Predecessor
- —
- Successor
- —
- Released
- March 10, 2026
- Model ID
google/gemini-embedding-2-preview- Openness
- Closed
- License
- —
- Input modalities
- text, image, file, audio, video
- Output modalities
- embeddings
- Modality
- text+image+file+audio+video->embeddings
- Tokenizer
- Gemini
- Max output tokens
- 7K
- Hugging Face
- —
- Source freshness
- Endpoints synced Oct 15, 2026, 1:45 PM UTC
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| google-ai-studio | 8K | $0.20 | $0.00 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter
Text provenance
Gemini app/webGoogle SynthID text watermarking
Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.
Official explanation