Qwen3 Embedding 8B vs Gemini Embedding 001: API price and specs

Qwen3 Embedding 8B is 93% cheaper than Gemini Embedding 001 on input price.

Qwen3 Embedding 8B is 93% cheaper than Gemini Embedding 001 on output price.

Qwen3 Embedding 8B is 93% cheaper than Gemini Embedding 001 on a 1M-in / 200k-out workload.

Qwen3 Embedding 8B has a 1900% larger context than Gemini Embedding 001.

Field	Qwen3 Embedding 8B	Gemini Embedding 001
Lowest input, per 1M	$0.01	$0.15 +1400%
Median input, per 1M	$0.01055	$0.15 +1321.8%
Lowest output, per 1M	$0.01049	$0.15 +1329.8%
Median output, per 1M	$0.01049	$0.15 +1329.8%
Lowest unit price	$0.001118 / request	—
Cost of 1M in + 200k out	$0.0121	$0.18 +1387.8%
Context	41K	2K +95%
Max output	33K	1 +100%
Providers	14	6 +57.1%
Regions	—	US
Accepts	text	text
Returns	embedding, embeddings, text, vector	embedding, text, vector
Type	Embeddings	Embeddings
Free option	no	no
Cheapest provider	deepinfra	aihubmix

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, Qwen3 Embedding 8B or Gemini Embedding 001?

Qwen3 Embedding 8B is 93% cheaper than Gemini Embedding 001 on input price. Qwen3 Embedding 8B is 93% cheaper than Gemini Embedding 001 on output price. Qwen3 Embedding 8B is 93% cheaper than Gemini Embedding 001 on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3 Embedding 8B or Gemini Embedding 001?

Qwen3 Embedding 8B: 41K tokens; Gemini Embedding 001: 2K tokens.

Where can I use both Qwen3 Embedding 8B and Gemini Embedding 001?

aihubmix, fastrouter, trustedrouter, vercel