Roar AI
DiscordGet started
All models
OpenAI · Embeddings

text-embedding-3-small API in India

text-embedding-3-small costs ₹1.94 per million tokens on Roar AI, charged in Indian rupees. Low-cost embeddings for search, recommendations and finding duplicates.

Price₹1.94per 1M tokens
Batch input₹0.97per 1M tokens
Context window8Ktokens

text-embedding-3-small API pricing in India

Price₹1.94 per 1M tokens · $0.02
Batch input₹0.97 per 1M tokens · $0.01
Batch outputFree per 1M tokens · Free

In Indian rupees, the currency your card is charged in, with the published US dollar rate beside each.

Every rate is published and stays the same from one request to the next. See every model.

Rates as of 15 November 2026. Prices are our published US dollar rates converted at ₹97 to the dollar, our rate for November — the same rate your card is charged.

Specs

Made byOpenAI
ReleasedJanuary 2024
TypeEmbeddings
Context window8K tokens
ReadsText
WeightsClosed
Processed inGlobal
Model idtext-embedding-3-small

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. It also 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.

What is text-embedding-3-small good for?

  • Semantic search and retrieval on a budget.
  • Finding duplicates and grouping similar items.
  • Recommendations.

text-embedding-3-small limitations

  • Noticeably weaker than text-embedding-3-large on multilingual search.
  • Each piece of text can be at most 8,192 tokens.

Using text-embedding-3-small from India

Roar AI provides access to text-embedding-3-small through the Roar AI gateway, charged in Indian rupees on one bill with every other model. Requests from India go through our gateway in Bangalore. Developers can use text-embedding-3-small alongside other supported models without a separate integration for every provider.

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. 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"],
)

Where is text-embedding-3-small processed?

Requests to text-embedding-3-small are processed on international infrastructure, outside India. The model directory says where each model is processed.

text-embedding-3-small FAQ

How much does text-embedding-3-small cost in India?

Price is ₹1.94 per 1M tokens; batch input is ₹0.97 per 1M tokens. Prices are our published US dollar rates converted at ₹97 to the dollar, our rate for November — the same rate your card is charged.

Can I pay for text-embedding-3-small in Indian rupees?

Yes. Your card is charged in Indian rupees, at our published rate for the month, on one bill with every other model you use. You do not need a separate OpenAI account.

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.

What is the context window of text-embedding-3-small?

text-embedding-3-small can read up to 8K tokens in one request.

Start using text-embedding-3-small

Create a free account, get an API key and call text-embedding-3-small with the OpenAI SDK, billed in Indian rupees.