text-embedding-3-large vs text-embedding-3-small: API price and specs

text-embedding-3-small is 85% cheaper than text-embedding-3-large on input price.

text-embedding-3-small is 85% cheaper than text-embedding-3-large on output price.

text-embedding-3-small is 85% cheaper than text-embedding-3-large on a 1M-in / 200k-out workload.

Field	text-embedding-3-large	text-embedding-3-small
Lowest input, per 1M	$0.10 +550%	$0.016
Median input, per 1M	$0.13 +550%	$0.02
Lowest output, per 1M	$0.10 +550%	$0.016
Median output, per 1M	$0.12 +550%	$0.018
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.12 +550%	$0.0192
Context	8K	8K
Max output	3K	2K +50%
Providers	9	9
Regions	—	EU, US
Accepts	text	text
Returns	embedding, embeddings, text, vector	embedding, embeddings, text, vector
Type	Embeddings	Embeddings
Free option	no	no
Cheapest provider	cometapi	cometapi

Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.

Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.

Providers selling both

aihubmix, azure, cometapi, fastrouter, impossibl, openai, trustedrouter, vercel, zenmux

Frequently asked questions

Which is cheaper, text-embedding-3-large or text-embedding-3-small?

text-embedding-3-small is 85% cheaper than text-embedding-3-large on input price. text-embedding-3-small is 85% cheaper than text-embedding-3-large on output price. text-embedding-3-small is 85% cheaper than text-embedding-3-large on a 1M-in / 200k-out workload.

Which has the larger context, text-embedding-3-large or text-embedding-3-small?

text-embedding-3-large: 8K tokens; text-embedding-3-small: 8K tokens.

Where can I use both text-embedding-3-large and text-embedding-3-small?

aihubmix, azure, cometapi, fastrouter, impossibl, openai, trustedrouter, vercel, zenmux