Gemini Embedding Experimental 03-07
Gemini embedding achieves a SOTA performance across many key dimensions including code, multi-lingual, and retrieval.
Specs
- Context
- —
- Max output
- —
- Input price
- —
- Output price
- —
- Released
- —
Context
- Context window
- —
- Max input
- 8.2K
- Max output
- —
Pricing
- Not published
Modalities
- Input
- Text
- Output
- Embedding
API
- API types
Reasoning
- Reasoning
- No
Info
- Status
- Retired
- Released
- —
- Knowledge cutoff
- —
Features
- Not published
How to call
1 provider
googlemodel = gemini-embedding-exp-03-07
embeddings
POSThttps://generativelanguage.googleapis.com/v1beta/models/{model}:embedContent
JSON
Standard format
{
"id": "gemini-embedding-exp-03-07",
"object": "model",
"created": null,
"owned_by": "google",
"name": "Gemini Embedding Experimental 03-07",
"api": {
"types": [
"embeddings"
]
},
"limits": {
"context": null,
"input": 8192,
"output": null
},
"modalities": {
"input": [
"text"
],
"output": [
"embedding"
]
},
"reasoning": {
"supported": false,
"efforts": []
},
"pricing": null,
"features": [],
"info": {
"status": "retired",
"release_date": null,
"knowledge_cutoff": null,
"description": "Gemini embedding achieves a SOTA performance across many key dimensions including code, multi-lingual, and retrieval.",
"docs": "https://ai.google.dev/gemini-api/docs/deprecations",
"verified_at": "2026-10-11"
}
}Official sources
2