text-embedding-3-small

Common Name: Text-embedding-3-small

OpenAI

Released on Jan 25, 2024 12:00 AM

Compare

Cost-efficient embedding model with improved performance over ada-002, supporting up to 8191 tokens.

Specifications

Context

8.2K

Maximum Output

1.5K

Inputtext

Outputvector

Performance (7-day Average)

Collecting…

Pricing

Input$0.02/MTokens

Batch Input$0.01/MTokens

Availability Trend (24h)

Performance Metrics (24h)

Similar Models

GPT-4

$33.00/$66.00/M

ctx8Kmax8Kavail—tps—

InOutCap

OpenAI's advanced language model with superior reasoning, creativity, and complex task handling capabilities.

GPT-4 (0613)

$33.00/$66.00/M

ctx8Kmax8Kavail—tps—

InOutCap

GPT-4 snapshot from June 2023 with improved function calling support. Optimized for complex reasoning tasks.

Text-embedding-ada-002

$0.11/—/M

ctx8Kmax2Kavail—tps—

InOut

Legacy embedding model generating 1536-dimensional vectors for semantic search and similarity tasks.

Text-embedding-3-large

$0.14/—/M

ctx8Kmax3Kavail—tps—

InOut

High-performance embedding model generating 3072-dimensional vectors for advanced semantic understanding.

API Usage

Note: This model uses the /v1/embeddings endpoint, not /v1/chat/completions.

python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ohmygpt.com/v1",
    api_key="your-api-key",
)

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The quick brown fox jumps over the lazy dog",
)

embedding = response.data[0].embedding
print(f"Embedding dimension: {len(embedding)}")

Batch Embedding

You can embed multiple texts in a single request:

python

response = client.embeddings.create(
    model="text-embedding-3-small",
    input=[
        "First document to embed",
        "Second document to embed",
        "Third document to embed",
    ],
)

for i, item in enumerate(response.data):
    print(f"Document {i}: {len(item.embedding)} dimensions")

Use Case

Description

Semantic Search

Find relevant documents based on meaning

Clustering

Group similar texts together

Classification

Categorize text by similarity to examples

RAG

Retrieval-Augmented Generation pipelines