OpenAI Embedding 3 Large
OpenAI Embedding 3 Large is a text embedding model from OpenAI with an 8,191 token context window.
OpenAILarge-scale text embeddings from OpenAI
OpenAI Embedding 3 Large (text-embedding-3-large) is a text embedding model developed and published by OpenAI, released in 2024. It converts text input into numerical vector representations that capture semantic meaning, enabling downstream tasks such as semantic search, clustering, classification, and retrieval-augmented generation. The model accepts up to 8,191 tokens of input and produces high-dimensional embeddings suitable for applications that require nuanced semantic similarity comparisons.
This model is the larger of OpenAI's third-generation embedding models, designed for use cases where embedding quality and representational depth are priorities. It is accessed via OpenAI's API and is well-suited for building search systems, recommendation engines, document retrieval pipelines, and other applications that depend on accurate vector similarity. Developers integrate it directly into their workflows without needing to manage model weights or infrastructure.
What OpenAI Embedding 3 Large supports
Text Embedding
Converts input text into dense numerical vectors that encode semantic meaning, supporting tasks like similarity search and clustering. Accepts up to 8,191 tokens per request.
Semantic Search
Enables retrieval of semantically related documents or passages by comparing embedding vectors rather than exact keyword matches.
Document Retrieval
Supports retrieval-augmented generation (RAG) pipelines by embedding documents and queries into a shared vector space for nearest-neighbor lookup.
Text Classification
Embedding vectors can be used as input features for downstream classifiers, enabling text categorization without task-specific fine-tuning.
Clustering
Groups semantically similar texts together by applying clustering algorithms to the produced embedding vectors.
API Integration
Accessed via OpenAI's REST API, returning embeddings as JSON arrays that integrate directly into existing data pipelines and vector databases.
Ready to build with OpenAI Embedding 3 Large?
Get Started FreeCommon questions about OpenAI Embedding 3 Large
What is the context window for OpenAI Embedding 3 Large?
The model supports a maximum input of 8,191 tokens per request. Text exceeding this limit must be chunked before embedding.
What output does the model produce?
The model outputs a numerical vector (array of floating-point numbers) representing the semantic content of the input text. It does not generate natural language responses.
How is this model priced?
Pricing information was not included in the available metadata. Current pricing can be found on OpenAI's official pricing page at platform.openai.com/docs/pricing.
What is the knowledge cutoff for this model?
As an embedding model, OpenAI Embedding 3 Large does not have a knowledge cutoff in the same way generative models do. It encodes text you provide rather than recalling stored facts.
What are common use cases for this model?
Common use cases include semantic search, document retrieval for RAG pipelines, text clustering, recommendation systems, and building features for downstream classification tasks.
Does the model support inputs other than text?
Based on the available metadata, the model accepts text input only. It does not support image, audio, or video inputs.
Explore similar models
OpenAIOpenAI Embedding 3 Small
OpenAI Embedding 3 Small is a text embedding model from OpenAI with an 8,191 token context window.
OpenAIGPT 5.6 Luna
GPT 5.6 Luna is a text and image-input model from OpenAI with a 1,050,000-token context window.
OpenAIGPT 5.6 Terra
GPT 5.6 Terra is a text generation model from OpenAI with a 1,050,000-token context window and image input support.
PerplexityPerplexity Embed v1 0.6B
Perplexity Embed v1 0.6B is a quantized embedding model from Perplexity with a 32,000-token context window.
GoogleGemini Embedding 2
Gemini Embedding 2 is a text embedding model from Google designed to convert text into dense vector representations.
Voyage AIVoyage 4
Voyage 4 is an embedding model from Voyage AI designed for semantic search and retrieval with a 32,000-token context window.
Start building with OpenAI Embedding 3 Large
No API keys required. Create AI-powered workflows with OpenAI Embedding 3 Large in minutes — free.