# Text Embedding 3 Large - Core.Today AI API

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

- **Provider**: OpenAI
- **Model ID**: text-embedding-3-large
- **Category**: LLM
- **Credits**: 0.24 per 1K tokens
- **Speed**: Fast
- **Quality**: High

## Model Specifications
- **Context Window**: 8K tokens
- **Max Output**: 0K tokens
- **Training Cutoff**: n/a
- **Supported Formats**: text
- **Compatible SDK**: OpenAI

### Token Pricing (per 1M tokens)
- **Input Tokens**: 241.54 credits ($0.16)
- **Output Tokens**: 0 credits ($0.00)

## Features
- 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

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

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/openai/v1/embeddings

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **input**: string | array - Text or array of texts to embed. Max 8,191 input tokens per item.
- **model**: string (default: text-embedding-3-large) - Model identifier.

### Optional
- **dimensions**: integer (default: 3072) - Output embedding dimensionality. Defaults to 3,072; can be reduced to shrink storage while preserving semantic quality.
- **encoding_format**: string (default: float) - Format of the returned embeddings: float or base64.
  Options: float, base64

## Examples

### Text Embedding
Generate high-quality embeddings for semantic search
```json
{
  "model": "text-embedding-3-large",
  "input": "What is the meaning of life?"
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

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

## Documentation
https://platform.openai.com/docs/guides/embeddings