Text Embedding 3 Small
Text Embedding 3 Small is OpenAI's cost-efficient embedding model, producing 1536-dimensional vectors with strong quality at 5x lower cost than the large variant. It delivers excellent performance for most retrieval and classification tasks, making it the default recommendation for production RAG systems.
Like its larger sibling, it supports Matryoshka representations for flexible dimensionality, enabling further cost savings when applications can tolerate slightly lower precision.
Key Features
1536-dimensional embeddings at 5x lower cost than Large
Strong retrieval performance for most use cases
Flexible dimensionality (Matryoshka)
8191 token input limit
Excellent cost-quality ratio
Ideal Use Cases
Production RAG systems at scale
Cost-efficient semantic search
Document classification and routing
Content recommendation engines
Technical Specifications
| Dimensions | 1536 (flexible) |
| Max Input | 8191 tokens |
| Modality | Text → Embedding |
| Provider | OpenAI |
| Category | Embedding |
| Tier | Cost-efficient |
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": "openai/text-embedding-3-small", 6 "messages": [ 7 { "role": "user", "content": "Hello, Text Embedding 3 Small!" } 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 3 Small now
Start using Text Embedding 3 Small instantly — 100 free credits, no credit card required. Access 343+ AI models through one platform.
More from OpenAI
Use ← → to navigate between models · Esc to go back
GPT-5.2
OpenAI's latest flagship with superior language understanding and generation.
GPT-5.2 Pro
Extended context and enhanced accuracy for professional workloads.
GPT-5.2 Chat
Optimized for multi-turn conversational interactions.
GPT-5.2 Codex
Top-tier code generation and software engineering assistant.