Gemini Embedding 001 vs text-embedding-3-large: API price and specs

text-embedding-3-large is 31% cheaper than Gemini Embedding 001 on input price.

text-embedding-3-large is 31% cheaper than Gemini Embedding 001 on output price.

text-embedding-3-large is 31% cheaper than Gemini Embedding 001 on a 1M-in / 200k-out workload.

text-embedding-3-large has a 300% larger context than Gemini Embedding 001.

Field	Gemini Embedding 001	text-embedding-3-large
Lowest input, per 1M	$0.15 +44.2%	$0.10
Median input, per 1M	$0.15 +15.4%	$0.13
Lowest output, per 1M	$0.15 +44.2%	$0.10
Median output, per 1M	$0.15 +28.2%	$0.12
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.18 +44.2%	$0.12
Context	2K +75%	8K
Max output	1 +100%	3K
Providers	6 +33.3%	9
Regions	US	—
Accepts	text	text
Returns	embedding, text, vector	embedding, embeddings, text, vector
Type	Embeddings	Embeddings
Free option	no	no
Cheapest provider	aihubmix	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, fastrouter, trustedrouter, vercel

Frequently asked questions

Which is cheaper, Gemini Embedding 001 or text-embedding-3-large?

text-embedding-3-large is 31% cheaper than Gemini Embedding 001 on input price. text-embedding-3-large is 31% cheaper than Gemini Embedding 001 on output price. text-embedding-3-large is 31% cheaper than Gemini Embedding 001 on a 1M-in / 200k-out workload.

Which has the larger context, Gemini Embedding 001 or text-embedding-3-large?

Gemini Embedding 001: 2K tokens; text-embedding-3-large: 8K tokens.

Where can I use both Gemini Embedding 001 and text-embedding-3-large?

aihubmix, fastrouter, trustedrouter, vercel