Gemma 3 12B IT vs Llama-3.2-11B-Vision-Instruct: API price and specs

Llama-3.2-11B-Vision-Instruct is 50% cheaper than Gemma 3 12B IT on input price.

Llama-3.2-11B-Vision-Instruct is 80% cheaper than Gemma 3 12B IT on output price.

Llama-3.2-11B-Vision-Instruct is 60% cheaper than Gemma 3 12B IT on a 1M-in / 200k-out workload.

Field	Gemma 3 12B IT	Llama-3.2-11B-Vision-Instruct
Lowest input, per 1M	$0.04 +100%	$0.02
Median input, per 1M	$0.05275 +3.1%	$0.05117
Lowest output, per 1M	$0.10 +400%	$0.02
Median output, per 1M	$0.15	$0.34 +130%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.06 +150%	$0.024
Context	131K	131K
Max output	131K	128K +2.3%
Providers	15	7 +53.3%
Regions	EU, GLOBAL, US	US
Accepts	image, image/gif, image/jpeg, image/png, image/webp, text	image, text
Returns	text	text
Type	Text models	Text models
Free option	yes	yes
Cheapest provider	kilo	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, cloudflare-workers-ai, deepinfra, edenai, nvidia, trustedrouter

Frequently asked questions

Which is cheaper, Gemma 3 12B IT or Llama-3.2-11B-Vision-Instruct?

Llama-3.2-11B-Vision-Instruct is 50% cheaper than Gemma 3 12B IT on input price. Llama-3.2-11B-Vision-Instruct is 80% cheaper than Gemma 3 12B IT on output price. Llama-3.2-11B-Vision-Instruct is 60% cheaper than Gemma 3 12B IT on a 1M-in / 200k-out workload.

Which has the larger context, Gemma 3 12B IT or Llama-3.2-11B-Vision-Instruct?

Gemma 3 12B IT: 131K tokens; Llama-3.2-11B-Vision-Instruct: 131K tokens.

Where can I use both Gemma 3 12B IT and Llama-3.2-11B-Vision-Instruct?

aihubmix, cloudflare-workers-ai, deepinfra, edenai, nvidia, trustedrouter