Model Details
Released
Dec 15, 2022
Context Length
8,192
Where is Text Embedding ADA-002 a perfect fit?
text-embedding-ada-002 is best suited for existing systems built on earlier embedding standards, where migration hasn’t yet occurred. Ideal for:
- Legacy semantic search and retrieval systems
- Older RAG pipelines relying on precomputed embeddings
- Applications requiring compatibility with stored vector databases
- Cost-sensitive deployments using stable, well-known models
- Internal tools built before newer embedding models were introduced
- Systems prioritising consistency over maximum embedding accuracy
- Legacy semantic search and retrieval systems
- Older RAG pipelines relying on precomputed embeddings
- Applications requiring compatibility with stored vector databases
- Cost-sensitive deployments using stable, well-known models
- Internal tools built before newer embedding models were introduced
- Systems prioritising consistency over maximum embedding accuracy
Quick Model Estimate
Your Text Embedding ADA-002 Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
📥 Input (1000)
—
📤 Output (1000)
—
Cost Breakdown
📥 Input
📤 Output
Prices are watched for changes and checked against the provider's own page.
Pricing
FAQs about Text Embedding ADA-002
What is Text Embedding ADA-002's context window?
Text Embedding ADA-002 has a context window of 8,192 tokens.