Back to all models
Get all the details on text-embedding-ada-002, an AI model from OpenAI. This page covers its token limits, pricing structure, key capabilities such as Anomaly Detection, Classification, Clustering, available API code samples, and performance strengths.
Key Metrics
Input Limit
No data tokens
Output Limit
No data tokens
Input Cost
$0.10/1M
Output Cost
N/A/1M
Sample API Code
from openai import OpenAI
client = OpenAI()
response = client.embeddings.create(
input="Your text string goes here",
model="text-embedding-ada-002"
)
embedding = response.data[0].embedding
print(embedding)Required Libraries
openai
openai
Notes
Improved, more performant version of the previous ada embedding model. Embeddings are a numerical representation of text used to measure relatedness. Useful for search, clustering, recommendations, anomaly detection, and classification tasks. This is an older embedding model compared to text-embedding-3-small/large.
Capabilities
Anomaly Detection
Classification
Clustering
embeddings
Measuring text relatedness
Recommendations
Search
Supported Data Types
Input Types
text
Output Types
other
Strengths & Weaknesses
Good at
Measuring text relatedness
Search
Clustering
Recommendations
Anomaly Detection
Classification
Additional Information
Latest Update
Dec 15, 2022
Knowledge Cutoff
No data