Text Embedding 3 Small

About Text Embedding 3 Small

Text Embedding 3 Small is OpenAI's efficient embedding model, delivering strong semantic search capability at lower cost. It produces 1536-dimensional embeddings that capture semantic meaning effectively while requiring less storage and compute than the large variant. The model achieves competitive performance on embedding benchmarks, offering excellent value for most retrieval applications. Text Embedding 3 Small supports configurable output dimensions for optimization. It's ideal for high-volume applications, cost-sensitive deployments, and scenarios where good retrieval quality suffices without maximum accuracy. For developers building semantic search and RAG systems at scale, Text Embedding 3 Small provides practical embedding capability with favorable economics.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

OpenAI Model Lineup

Compare all models from OpenAI to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Qwen3 Embedding 4B

Alibaba Qwen

Input: $0.02

Output: Free

Context: 33k

LiquidAI/LFM2-8B-A1B

Other

Input: $0.01

Output: $0.02

Context: 33k

LiquidAI/LFM2-2.6B

Other

Input: $0.01

Output: $0.02

Context: 33k

GTE-Large

Other

Input: $0.01

Output: Free

Context: 512

💡 Cheaper Alternatives

Cross Brand

🚀 Quick Start

Get started with Text Embedding 3 Small API

from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model="openai/text-embedding-3-small",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision