OpenAI

text-embedding-ada-002 API Pricing

Older embedding model, predecessor to the text-embedding-3 family. Text-only.

Verified against OpenAI’s pricing page on 2026-07-02.

View source ↗

Facts

Legacy

Specs

  • Familytext-embedding-ada
  • API IDtext-embedding-ada-002
  • ModalityEmbedding
  • Context window
  • Max output
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$0.10 / 1M tokens
  • Output
  • Cached input
  • Cache write
  • Batch discount

Capabilities

embedding

Notes

Older embedding model, predecessor to the text-embedding-3 family. Text-only.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$8.00

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$18.00

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$10.00

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

text-embedding-ada-002 pricing FAQ

How much does text-embedding-ada-002 cost per 1M tokens?
text-embedding-ada-002 costs $0.10 per 1M input tokens.
How much does text-embedding-ada-002 cost per request?
We can't compute an exact per-request cost for text-embedding-ada-002 — some price fields aren't published.
Is text-embedding-ada-002 cheaper than chat-latest?
text-embedding-ada-002 is cheaper than chat-latest on input tokens, by about 98%.
Does text-embedding-ada-002 have cache pricing?
No cache discount is documented for text-embedding-ada-002 on the provider's pricing page.