text-embedding-3-large
OpenAI’s most accurate embedding model, and the better one for languages other than English.
About text-embedding-3-large
Embeddings turn text into lists of numbers that capture its meaning, so you can search by meaning rather than keywords, find similar documents, or let an assistant draw on your own files. text-embedding-3-large is OpenAI’s most accurate: 3,072 numbers per text by default, scoring 64.6% on the MTEB benchmark.
Its real advantage is outside English. On MIRACL, a multilingual search test, it scores 54.9% against 44.0% for the small version. You can also shorten its vectors to save storage — OpenAI says a 256-number version still beats its older ada-002 model.
Where it’s strong
Search across documents in more than one language.
Retrieval for assistants that answer from your own files.
Grouping and classifying documents.
Where to be careful
Costs more and needs more storage than text-embedding-3-small, for a modest gain in English.
Each piece of text can be at most 8,192 tokens, so long documents need splitting first.
Price
Every rate is published and stays the same from one request to the next. See every model.
Specs
text-embedding-3-largeCall 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-large",
input=["Quarterly sales report, western province"],
)Compare text-embedding-3-large
Questions
How much does text-embedding-3-large cost?
Price is $0.1495 per 1M tokens; batch input is $0.0747 per 1M tokens. The rate is published and does not change from one request to the next.
Can I use text-embedding-3-large 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-large to another model is a change to one word in your code.
Is text-embedding-3-large open source?
No. OpenAI does not publish the weights, so it is only available through an API like this one.