Gemini Embedding 2
Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space
- Context
- 8K
- Released
- 5mo ago
- Input / 1M tokens
- $0.20
- Output / 1M tokens
- $0.00
Sources:models.devOpenRouter
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
- April 22, 2026
- Model ID
google/gemini-embedding-2- 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
- Knowledge cutoff
- 2025-11
- Hugging Face
- —
- Source freshness
- Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
- Source model
- google/gemini-embedding-2
- Source family
- gemini
- Last updated
- 2026-04-22
- Knowledge cutoff
- 2025-11
- Model context
- 8K
- Model output limit
- 3K
- Open weights
- No
- File attachments
- Yes
- Reasoning
- No
- Tool calling
- No
- Temperature control
- No
Complete source record (JSON)
{
"id": "google/gemini-embedding-2",
"name": "Gemini Embedding 2",
"description": "Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space",
"family": "gemini",
"last_updated": "2026-04-22",
"knowledge": "2025-11",
"attachment": true,
"reasoning": false,
"tool_call": false,
"temperature": false,
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"pdf"
],
"output": [
"text"
]
},
"limit": {
"context": 8192,
"output": 3072
},
"release_date": "2026-04-22",
"open_weights": false
}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-vertex/us | 8K | $0.20 | $0.00 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/global | 8K | $0.20 | $0.00 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/usBatch pricing | 8K | $0.20 | $0.00 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/globalBatch pricing | 8K | $0.20 | $0.00 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-ai-studio | 8K | $0.20 | $0.00 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-ai-studioBatch pricing | 8K | $0.20 | $0.00 | — | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/eu | 8K | $0.22 | $0.00 | — | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| google-vertex/euBatch pricing | 8K | $0.22 | $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