Qwen3 Embedding 8B vs text-embedding-3-large: API price and specs

Qwen3 Embedding 8B is 90% cheaper than text-embedding-3-large on input price.

Qwen3 Embedding 8B is 90% cheaper than text-embedding-3-large on output price.

Qwen3 Embedding 8B is 90% cheaper than text-embedding-3-large on a 1M-in / 200k-out workload.

Qwen3 Embedding 8B has a 400% larger context than text-embedding-3-large.

Field	Qwen3 Embedding 8B	text-embedding-3-large
Lowest input, per 1M	$0.01	$0.10 +940%
Median input, per 1M	$0.01055	$0.13 +1132.2%
Lowest output, per 1M	$0.01049	$0.10 +891.3%
Median output, per 1M	$0.01049	$0.12 +1015.2%
Lowest unit price	$0.001118 / request	—
Cost of 1M in + 200k out	$0.0121	$0.12 +931.6%
Context	41K	8K +80%
Max output	33K	3K +90.6%
Providers	14	9 +35.7%
Regions	—	—
Accepts	text	text
Returns	embedding, embeddings, text, vector	embedding, embeddings, text, vector
Type	Embeddings	Embeddings
Free option	no	no
Cheapest provider	deepinfra	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, impossibl, trustedrouter, vercel

Frequently asked questions

Which is cheaper, Qwen3 Embedding 8B or text-embedding-3-large?

Qwen3 Embedding 8B is 90% cheaper than text-embedding-3-large on input price. Qwen3 Embedding 8B is 90% cheaper than text-embedding-3-large on output price. Qwen3 Embedding 8B is 90% cheaper than text-embedding-3-large on a 1M-in / 200k-out workload.

Which has the larger context, Qwen3 Embedding 8B or text-embedding-3-large?

Qwen3 Embedding 8B: 41K tokens; text-embedding-3-large: 8K tokens.

Where can I use both Qwen3 Embedding 8B and text-embedding-3-large?

aihubmix, fastrouter, impossibl, trustedrouter, vercel