Google · MODEL PROFILE
Gemini Embedding 2 Preview
Accepts text, images, files, audio, video and produces embeddings.
At a glance
- Provider
- Type
- API model
- Access
- OpenRouter API; availability and price can vary by routed provider.
- Context
- 8,192 tokens
- Maximum output
- 7,372 tokens
- License / weights
- Not documented
- Pricing notes
- This model produces media, embeddings or other non-text outputs. Text token prices do not describe its complete cost.
- Input modalities
- text, image, file, audio, video
- Output modalities
- embeddings
The practical trade-offs
Documented strengths
No saved strengths assessment.
Limitations to check
- No normalized editorial score or independently checked benchmark is assigned to this catalogue addition.
FOLLOW THE SOURCE
2 source linksEvidence & conditions
Source reports, measured results, and editorial assessments are separate evidence types. Source dates do not imply a new benchmark run. Capture dates are compared with this catalogue snapshot (Sep 11, 2026), not today’s date.
- OpenRouter catalogue Capture date not recorded
- OpenRouter catalogue Capture date not recorded
No comparable benchmark observations are recorded for this entry.