OpenAI

text-embedding-3-small

Efficient, high-quality embeddings for broad applications.

Lower cost than large modelsGood performance-to-cost ratioFaster inference timesSuitable for many RAG use cases

Where it ranks today

Best for / Not great for

Best for
  • Cost-effective RAG
  • Real-time search
  • General text classification
  • Applications with high request volumes
Not great for
  • Highly nuanced semantic understanding
  • Extremely complex classification tasks
  • Scenarios where only the absolute highest accuracy matters

Why it ranks here

As a more affordable and faster alternative to its larger sibling, text-embedding-3-small is seeing increased adoption for applications where cost and speed are critical. It maintains strong performance, making it a practical choice for many common RAG and search tasks.

30-day trend

Score breakdown

Search trends91
Benchmarks89
Developer buzz92
News mentions90

Pricing

API: $0.00 in · $0.00 out per 1M tokens · Consumer: $0.00/mo

Pricing plans

Free Tier
Get started with basic embedding needs.
Free
  • Limited API calls
  • Access to small models
  • Standard API features
Sign up free
Popular
Pay-as-you-go
Most cost-effective embeddings at scale.
$0 /usage
  • text-embedding-3-small
  • Low cost per token
  • High QPS
  • Global infrastructure
View pricing
Enterprise
Dedicated support and optimized performance.
Custom
  • Volume discounts
  • Premium support
  • Custom solutions
  • Enhanced security
Contact sales
Compare with another modelHow is this score calculated? →Snapshot 2026-09-05