text-embedding-3-small vs text-embedding-ada-002: API price and specs

text-embedding-3-small is 80% cheaper than text-embedding-ada-002 on input price.

text-embedding-3-small is 80% cheaper than text-embedding-ada-002 on output price.

text-embedding-3-small is 80% cheaper than text-embedding-ada-002 on a 1M-in / 200k-out workload.

Field	text-embedding-3-small	text-embedding-ada-002
Lowest input, per 1M	$0.016	$0.08 +400%
Median input, per 1M	$0.02	$0.10 +400%
Lowest output, per 1M	$0.016	$0.08 +400%
Median output, per 1M	$0.018	$0.09 +400%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.0192	$0.096 +400%
Context	8K	8K
Max output	2K	2K
Providers	9	7 +22.2%
Regions	EU, US	—
Accepts	text	text
Returns	embedding, embeddings, text, vector	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, openai, trustedrouter, vercel

Frequently asked questions

Which is cheaper, text-embedding-3-small or text-embedding-ada-002?

text-embedding-3-small is 80% cheaper than text-embedding-ada-002 on input price. text-embedding-3-small is 80% cheaper than text-embedding-ada-002 on output price. text-embedding-3-small is 80% cheaper than text-embedding-ada-002 on a 1M-in / 200k-out workload.

Which has the larger context, text-embedding-3-small or text-embedding-ada-002?

text-embedding-3-small: 8K tokens; text-embedding-ada-002: 8K tokens.

Where can I use both text-embedding-3-small and text-embedding-ada-002?

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