text-embedding-3-small is OpenAI's smaller, more efficient text embedding model for search, clustering, recommendations and classification. It accepts up to 8,192 input tokens and returns 1,536-dimensional embeddings by default, which can be shortened with the dimensions parameter.
Modalities
In / out price
$0.025 / $0.025per 1M
Context
8K
Max output
–
Updated
Oct 22, 2026
Providers
1 routeCompare providers by price, privacy, and speed.
| Anonymous | $0.025 | $0.025 | — | 8K | – | — | — |
Privacy
1 / 4Anonymous routing
Anonymous tier
- Anonymous
- Private
- TEE
- E2EE
Your identity is hidden from the inference provider. The inference provider can see prompt content; zero retention is not guaranteed. Learn more
Features
1Embeddings
Uptime
FAQ
Common questions about Text Embedding 3 Small.