text-embedding-3-small
Low-cost embeddings for search, recommendations and finding duplicates.
About text-embedding-3-small
text-embedding-3-small is the inexpensive half of OpenAI’s embedding pair. It produces 1,536 numbers per text — the same size as the older ada-002, so it drops into an existing search index — and beats ada-002 on both the MTEB benchmark (62.3% against 61.0%) and multilingual search.
For English-language search and recommendations it is close enough to the large model that the saving usually wins. Where documents are in several languages, the large model’s lead is wide enough to be worth paying for.
Where it’s strong
Semantic search and retrieval on a budget.
Finding duplicates and grouping similar items.
Recommendations.
Where to be careful
Noticeably weaker than text-embedding-3-large on multilingual search.
Each piece of text can be at most 8,192 tokens.
Price
Every rate is published and stays the same from one request to the next. See every model.
Specs
text-embedding-3-smallCall it
Use the OpenAI SDK you already have — point it at Roar AI and name the model. Read the docs.
from openai import OpenAI
client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")
vectors = client.embeddings.create(
model="text-embedding-3-small",
input=["Quarterly sales report, western province"],
)Compare text-embedding-3-small
Questions
How much does text-embedding-3-small cost?
Price is $0.023 per 1M tokens; batch input is $0.0115 per 1M tokens. The rate is published and does not change from one request to the next.
Can I use text-embedding-3-small alongside other models?
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from text-embedding-3-small to another model is a change to one word in your code.
Is text-embedding-3-small open source?
No. OpenAI does not publish the weights, so it is only available through an API like this one.