Text Embedding 004
Text Embedding 004 is Google's previous-generation embedding model, offering proven reliability and broad deployment across production systems. It produces 768-dimensional vectors with strong quality for most retrieval and classification tasks.
While the newer 005 model offers improved task-aware embeddings, 004 remains a solid choice for existing deployments and teams that value stability over cutting-edge features.
Key Features
Proven 768-dimensional embeddings
Broad deployment track record
Strong multilingual support
Reliable quality for production use
Stable API behavior
Ideal Use Cases
Existing production search systems
Stable RAG deployments
Multilingual document retrieval
Systems not yet ready for model migration
Technical Specifications
| Dimensions | 768 |
| Modality | Text → Embedding |
| Provider | |
| Category | Embedding |
| Status | Production stable |
API Usage
1 curl -X POST https://api.vincony.com/v1/chat/completions \ 2 -H "Authorization: Bearer YOUR_API_KEY" \ 3 -H "Content-Type: application/json" \ 4 -d '{ 5 "model": "google/text-embedding-004", 6 "messages": [ 7 { "role": "user", "content": "Hello, Text Embedding 004!" } 8 ] 9 }'
Replace YOUR_API_KEY with your Vincony API key. OpenAI-compatible endpoint — works with any OpenAI SDK.
Compare with Another Model
Frequently Asked Questions
Try Text Embedding 004 now
Start using Text Embedding 004 instantly — 100 free credits, no credit card required. Access 343+ AI models through one platform.
More from Google
Use ← → to navigate between models · Esc to go back