text-embedding-ada-002
text-embedding-ada-002 is an older text embedding model that remains in the public catalog. It serves existing retrieval and matching systems through the embeddings endpoint.
An existing index is tied to its embedding model
The model has a listed price of $0.10 per million input tokens. The newer v3 embedding models introduce a different generation of representations. The catalog continues to list ada-002 separately rather than treating its name as a v3 alias.text-embedding-ada-002 official model documentation
Rebuild vectors when migrating an index
Practical guidance. Do not mix document vectors from one embedding model with query vectors from another. Build a separate comparison index, evaluate relevant-result quality and then switch the document and query paths together. Keep retrieval measurements tied to the exact model.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | text-embedding-ada-002 |
| Input price | 0.1 USD per million tokens Published embedding input-token rate text-embedding-ada-002 official model documentation |
| Output | Numerical text vectorstext-embedding-ada-002 official model documentation |
| API routes | Batch (v1/batch); Embeddings (v1/embeddings)text-embedding-ada-002 official model documentation |
Related models
- text-embedding-3-small
OpenAI · OpenAI embeddings
text-embedding-3-small provides text vectors for search and relatedness tasks.
Launch date not confirmedAPI - text-embedding-3-large
OpenAI · OpenAI embeddings
text-embedding-3-large converts text into vectors for matching, retrieval and grouping.
Launch date not confirmedAPI