Introducing text-embedding-3-largeOpenAIReleased January 25, 2024

text-embedding-3-large

OpenAI’s most capable embedding model, providing 3072-dimensional vector representations for high-precision semantic search.

embeddingsProprietary API$0.13 / 1M tok (3072 dims)Context: 8.191K (8,191 tokens)

Technical Specifications

Architecture Type
High-Capacity Matryoshka Representation Transformer
Total Parameters
High-Capacity Dense
Context Window
8.191K (8,191 tokens)
Max Output Tokens
3.072K (3,072 tokens)
Knowledge Cutoff
September 2021
Supported Modalities
text
License & Access
OpenAI Business Terms

Benchmark Evaluations

Mteb
64.6
Miracl
54.9

Deep Architectural Overview

text-embedding-3-large delivers state-of-the-art multilingual text retrieval, clustering, and recommendation embeddings. It scales from 256 to 3072 dimensions, optimizing precision on technical, legal, and multi-domain datasets.

Strengths & Considerations

Core Strengths
  • Highest MTEB retrieval accuracy in OpenAI catalog
  • 3072-dimensional semantic density
  • Flexible truncation to 256/1024 dimensions
Known Limitations
  • Higher vector database storage requirements than small model

Token & API Pricing

Input Tokens (1M)$0.13
Output Tokens (1M)Contact
Pricing is verified directly against OpenAI's developer documentation and API rate sheets.

Similar & Alternative Models

Explore other frontier models from OpenAI and comparable reasoning engines.

Browse all models
OpenAI

OpenAI GPT-6 model for focused, high-volume workloads where cost efficiency is the priority.

1.05M ctxUSD 0.10 / 1M input tok; USD 0.50 / 1M output tok
OpenAI

OpenAI GPT-6 model built for complex coding and agentic workflows, balancing intelligence and cost.

1.05M ctxUSD 2 / 1M input tok; USD 10 / 1M output tok
OpenAI

OpenAI’s premier sixth-generation frontier model, built for the most demanding end-to-end software engineering and scientific research tasks.

1.05M ctx$10.00 / 1M tok (GPT-6 Frontier)