OpenAI: Text Embedding 3 Small
Embeddingopenai/text-embedding-3-smallText Embedding 3 Small is OpenAI's improved, more performant successor to the ada embedding model. It converts text into numerical vectors whose distances measure how closely two pieces of text are related, covering search, clustering, recommendations, anomaly detection, and classification. Input limit: 8K tokens per request. At $0.02/M input tokens it is the lowest-cost option in the Text Embedding 3 pair, which makes it the practical default for embedding large document sets or high-traffic retrieval. Accessible via the OpenAI-compatible protocol through Ofox.
Context Window
8K
Max Output Tokens
8K
Released
2025-10-30
Available Providers
Azure
Supported Protocols
openai
Providers
Azure
-20%Input Tokens
$0.016/M
$0.02/M
Output Tokens
$0/M
Web Search
$0.035/R
Protocols
openai
/v1/embeddingsCode Examples
from openai import OpenAIclient = OpenAI(base_url="https://api.ofox.ai/v1",api_key="YOUR_OFOX_API_KEY",)response = client.embeddings.create(model="openai/text-embedding-3-small",input="Hello, world!",)print(response.data[0].embedding[:5])
Related Models
Frequently Asked Questions
OpenAI: Text Embedding 3 Small on Ofox.ai costs $0.02/M per million input tokens and $0 per million output tokens. Pay-as-you-go, no monthly fees.
OpenAI: Text Embedding 3 Small supports a context window of 8K tokens with max output of 8K tokens, allowing you to process large documents and maintain long conversations.
Simply set your base URL to https://api.ofox.ai/v1 and use your Ofox API key. The API is OpenAI-compatible โ just change the base URL and API key in your existing code.