/
ModelsSupportEnterpriseBlog
500+ AI Model API, All In One API.Just In CometAPI
Models API
Developer
Quick StartDocumentationAPI Dashboard
Resources
AI ModelsBlogEnterpriseChangelogAbout
2025 CometAPI. All right reserved.Privacy PolicyTerms of Service
Home/Models/OpenAI/text-embedding-ada-002
O

text-embedding-ada-002

Input:$0.08/M
Output:$0.08/M
An Ada-based text embedding model optimized for various NLP tasks.
New
Commercial Use
Overview
Features
Pricing
API

Technical Specifications of text-embedding-ada-002

SpecificationDetails
Model IDtext-embedding-ada-002
Model TypeText embedding model
Core ArchitectureAda-based embedding architecture
Primary Use CaseConverting text into dense vector representations for NLP workflows
Input ModalityText
Output ModalityEmbedding vectors
Optimization FocusSemantic similarity, clustering, classification, search, and retrieval
Integration CategoryAPI-based model access
Suitable ForDevelopers building semantic search, recommendation, and text analysis systems

What is text-embedding-ada-002?

text-embedding-ada-002 is an Ada-based text embedding model optimized for various NLP tasks. It transforms text input into numerical vector representations that preserve semantic meaning, making it useful for applications that need to compare, organize, retrieve, or analyze text efficiently.

This model is well-suited for use cases such as semantic search, document ranking, duplicate detection, clustering, recommendation pipelines, and downstream machine learning systems that rely on high-quality text embeddings. By representing similar pieces of text with nearby vectors, text-embedding-ada-002 helps developers build systems that understand relationships between words, sentences, and documents beyond exact keyword matches.

Main features of text-embedding-ada-002

  • Semantic text representation: Converts text into dense embeddings that capture contextual and semantic relationships.
  • Search and retrieval support: Useful for semantic search, nearest-neighbor lookup, and retrieval-augmented workflows.
  • Clustering and classification readiness: Embeddings can be used as features for grouping, labeling, and organizing content.
  • Recommendation potential: Helps power recommendation systems by measuring similarity across text items.
  • Scalable NLP integration: Fits easily into production pipelines that need fast and repeatable vector generation.
  • Broad task applicability: Suitable for multiple NLP scenarios, including ranking, deduplication, and content discovery.

How to access and integrate text-embedding-ada-002

Step 1: Sign Up for API Key

Sign up on the CometAPI platform and generate your API key from the dashboard. After obtaining the key, store it securely and use it to authenticate all requests to the API.

Step 2: Send Requests to text-embedding-ada-002 API

Use the model ID text-embedding-ada-002 in your API request body when calling the embeddings endpoint. Example:

curl https://api.cometapi.com/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_COMETAPI_KEY" \
  -d '{
    "model": "text-embedding-ada-002",
    "input": "Sample text to embed"
  }'

Step 3: Retrieve and Verify Results

After sending your request, parse the response to retrieve the embedding vector and confirm that the returned model field is text-embedding-ada-002. You can then store the vector in your database, vector index, or downstream application for similarity search, ranking, clustering, or other NLP tasks.

Features for text-embedding-ada-002

Explore the key features of text-embedding-ada-002, designed to enhance performance and usability. Discover how these capabilities can benefit your projects and improve user experience.

Pricing for text-embedding-ada-002

Explore competitive pricing for text-embedding-ada-002, designed to fit various budgets and usage needs. Our flexible plans ensure you only pay for what you use, making it easy to scale as your requirements grow. Discover how text-embedding-ada-002 can enhance your projects while keeping costs manageable.
Comet Price (USD / M Tokens)Official Price (USD / M Tokens)Discount
Input:$0.08/M
Output:$0.08/M
Input:$0.1/M
Output:$0.1/M
-20%

Sample code and API for text-embedding-ada-002

Access comprehensive sample code and API resources for text-embedding-ada-002 to streamline your integration process. Our detailed documentation provides step-by-step guidance, helping you leverage the full potential of text-embedding-ada-002 in your projects.

More Models