OpenAI
text-embedding-3-small token cost calculator
OpenAI small embedding model at $0.02 per 1M input tokens. Output column stays $0 — embeddings only bill input.
Published list rates
Input
$0.02
per 1M tokens
Context window
8,192
tokens
Pricing source: OpenAI API pricing
Token cost calculator
The source publishes one processed-token rate rather than separate input and output prices. The table below applies that single rate.
| Processed tokens | Total cost |
|---|---|
| 1,000,000 | $0.02 |
| 10,000,000 | $0.2 |
| 100,000,000 | $2.00 |
| 1,000,000,000 | $20.00 |
Cost profile
- This item uses one $0.02 rate per 1 million processed tokens; the cited source does not publish a separate output rate.
- Filling the 8,192-token context window with input alone would cost about $0.000164, before any output.
How the text estimate works
For rough planning, CostUse uses about four characters per token and about 0.75 words per token. Actual tokenization changes with language, model, formatting, and special tokens.
These results use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the final invoice.
Questions about this rate
What is the text-embedding-3-small price per 1 million tokens?
$0.02 per 1 million processed tokens, according to the source checked on 2026-07-30. This page has no separate output price.
How much do 100 million tokens cost on text-embedding-3-small?
About $2.00 at the published linear rate, before provider-specific discounts or conditions.
Is the text estimate exact?
No. The character- and word-based token conversion is approximate. Use the provider’s tokenizer and billing documentation before approving a budget.