Text Embedding 3 Large

About Text Embedding 3 Large

Text Embedding 3 Large is OpenAI's most capable embedding model, generating high-quality vector representations for semantic search and retrieval. It produces 3072-dimensional embeddings that capture nuanced semantic meaning, enabling highly accurate similarity matching. The model achieves state-of-the-art performance on embedding benchmarks including MTEB, demonstrating exceptional capability for real-world retrieval tasks. Text Embedding 3 Large supports configurable output dimensions, allowing optimization for specific use cases. It's ideal for applications requiring maximum retrieval accuracy, including enterprise search, RAG systems, and recommendation engines. For developers building high-stakes retrieval applications where accuracy justifies premium pricing, Text Embedding 3 Large provides OpenAI's best embedding capability.

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

Mistral Small 3

Mistral

Input: $0.05

Output: $0.08

Context: 33k

Gemma 3 12B

Google

Input: $0.03

Output: $0.10

Context: 131k

Granite 4.0 Micro

IBM Granite

Input: $0.02

Output: $0.11

Context: 131k

Qwen2.5 7B Instruct

Alibaba Qwen

Input: $0.04

Output: $0.10

Context: 33k

💡 Cheaper Alternatives

Same Brand (OpenAI)

Cross Brand

🚀 Quick Start

Get started with Text Embedding 3 Large API

from openai import OpenAI
client = OpenAI()

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

Continue Your Decision