OpenAI

text-embedding-3-large API Pricing

OpenAI's "most capable embedding model." Embeddings are priced on input tokens only. Model page did not clearly state a differentiated Batch API rate.

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

View source ↗

Facts

Specs

  • Familytext-embedding-3
  • API IDtext-embedding-3-large
  • ModalityEmbedding
  • Context window
  • Max output
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$0.13 / 1M tokens
  • Output
  • Cached input
  • Cache write
  • Batch discount

Capabilities

embedding

Notes

OpenAI's "most capable embedding model." Embeddings are priced on input tokens only. Model page did not clearly state a differentiated Batch API rate.

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

$10.40

RAG pipeline

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

$23.40

Batch summarization

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

$13.00

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

text-embedding-3-large pricing FAQ

How much does text-embedding-3-large cost per 1M tokens?
text-embedding-3-large costs $0.13 per 1M input tokens.
How much does text-embedding-3-large cost per request?
We can't compute an exact per-request cost for text-embedding-3-large — some price fields aren't published.
Is text-embedding-3-large cheaper than text-embedding-3-small?
text-embedding-3-large is more expensive than text-embedding-3-small on input tokens, by about 550%.
Does text-embedding-3-large have cache pricing?
No cache discount is documented for text-embedding-3-large on the provider's pricing page.