Text Embedding Ada 002
Text Embedding Ada 002 is OpenAI's legacy embedding model, still widely deployed in existing production systems. While superseded by the Embedding 3 family in terms of quality and flexibility, Ada 002 remains available for backward compatibility and systems that depend on its specific vector characteristics.
Many organizations continue to use Ada 002 because migrating embedding models requires re-embedding entire document collections — a significant operational effort for large-scale deployments.
Key Features
1536-dimensional embeddings
Proven reliability across millions of deployments
Backward compatibility for existing systems
8191 token input limit
Well-understood performance characteristics
Ideal Use Cases
Legacy system maintenance and compatibility
Existing RAG pipelines not ready for migration
Applications with Ada 002-specific optimizations
Stable production embeddings with known behavior
Example Prompts for Text Embedding Ada 002
Technical Specifications
| Dimensions | 1536 |
| Max Input | 8191 tokens |
| Modality | Text → Embedding |
| Provider | OpenAI |
| Category | Embedding |
| Status | Legacy (still supported) |
Frequently Asked Questions
Try Text Embedding Ada 002 now
Start using Text Embedding Ada 002 instantly — 100 free credits, no credit card required. Access 750+ AI models through one platform.