Skip to main content
Core.Today
|
OpenAIFastHigh

Text Embedding 3 Large

OpenAI's most capable text embedding model. Generates high-quality vector representations for semantic search, clustering, and similarity tasks where retrieval accuracy matters most.

242/0credits
input / output ยท per 1M tokens
Highest-quality OpenAI text embeddings
8,191 token max input per item
Default output dimensions: 3,072
dimensions parameter can shorten embeddings
Optimized for semantic search, clustering, classification, and RAG

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Model Specifications

Context Window
8K
tokens
Max Output
0
tokens
Training Cutoff
n/a
Compatible SDK
OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens242$0.16
Output Tokens0$0.00

* 1,500 credits โ‰ˆ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/openai/v1/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "text-embedding-3-large",
  "input": "What is the meaning of life?"
}'

Parameters

ParameterTypeRequiredDefaultDescription
inputstring | arrayYes-Text or array of texts to embed. Max 8,191 input tokens per item.
modelstringYestext-embedding-3-largeModel identifier.
dimensionsintegerNo3072Output embedding dimensionality. Defaults to 3,072; can be reduced to shrink storage while preserving semantic quality.
encoding_formatstringNofloatFormat of the returned embeddings: float or base64.
floatbase64

Examples

Text Embedding

Generate high-quality embeddings for semantic search

curl -X POST "https://api.core.today/llm/openai/v1/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "text-embedding-3-large",
  "input": "What is the meaning of life?"
}'

Tips & Best Practices

1Max input: 8,191 tokens per item โ€” split long documents into chunks first
2Default output: 3,072 dimensions; use the dimensions parameter to shorten embeddings and save storage
3Choose this over text-embedding-3-small when retrieval accuracy matters more than cost
4Use the same model for indexing and querying โ€” embeddings from different models are not comparable
5Batch multiple texts in a single request for efficiency
6Combine with vector databases for RAG pipelines

Use Cases

Semantic search
Document clustering
Similarity matching
Recommendation systems
RAG (Retrieval-Augmented Generation)