text-embedding-3-small
text-embedding-3-small provides text vectors for search and relatedness tasks. Its listed token price is lower than both the large v3 model and ada-002.
A small embedding model still allows shorter vectors
Its default output has 1,536 dimensions, and the dimensions parameter can reduce that length. The listed rate is $0.02 per million input tokens. The API supports individual embedding requests and Batch processing.text-embedding-3-small official model documentationOpenAI embedding dimensions and retrieval guide
Inspect retrieval failures before changing models
Practical guidance. For a support knowledge base, compare missed articles, ambiguous terms and multilingual queries. Poor document splitting or weak source material can limit retrieval even with a larger model. Change one part of the retrieval pipeline at a time.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API |
| Model identifiers | text-embedding-3-small |
| Input price | 0.02 USD per million tokens Published embedding input-token rate text-embedding-3-small official model documentation |
| Output | Numerical text vectorstext-embedding-3-small official model documentation |
| API routes | Batch (v1/batch); Embeddings (v1/embeddings)text-embedding-3-small official model documentation |
Related models
- text-embedding-3-large
OpenAI · OpenAI embeddings
text-embedding-3-large converts text into vectors for matching, retrieval and grouping.
Launch date not confirmedAPI - text-embedding-ada-002
OpenAI · OpenAI embeddings
text-embedding-ada-002 is an older text embedding model that remains in the public catalog.
Launch date not confirmedAPI