Llama Guard 4 12B vs Nemotron 3.5 Content Safety: API price and specs

Nemotron 3.5 Content Safety is 65% cheaper than Llama Guard 4 12B on input price.

Llama Guard 4 12B is 4% cheaper than Nemotron 3.5 Content Safety on output price.

Nemotron 3.5 Content Safety is 54% cheaper than Llama Guard 4 12B on a 1M-in / 200k-out workload.

Llama Guard 4 12B has a 25% larger context than Nemotron 3.5 Content Safety.

Field	Llama Guard 4 12B	Nemotron 3.5 Content Safety
Lowest input, per 1M	$0.14 +188%	$0.05
Median input, per 1M	$0.18	$0.20 +11.1%
Lowest output, per 1M	$0.14	$0.15 +4.2%
Median output, per 1M	$0.18	$0.20 +11.1%
Lowest unit price	—	—
Cost of 1M in + 200k out	$0.17 +116%	$0.08
Context	164K	131K +20%
Max output	131K	131K
Providers	8 +20%	10
Regions	US	US
Accepts	image, text	image, image/gif, image/jpeg, image/png, text
Returns	text	text
Type	Moderation	Moderation
Free option	yes	yes
Cheapest provider	kilo	vultr

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

deepinfra, edenai, fastrouter, kilo, nvidia, openrouter

Frequently asked questions

Which is cheaper, Llama Guard 4 12B or Nemotron 3.5 Content Safety?

Nemotron 3.5 Content Safety is 65% cheaper than Llama Guard 4 12B on input price. Llama Guard 4 12B is 4% cheaper than Nemotron 3.5 Content Safety on output price. Nemotron 3.5 Content Safety is 54% cheaper than Llama Guard 4 12B on a 1M-in / 200k-out workload.

Which has the larger context, Llama Guard 4 12B or Nemotron 3.5 Content Safety?

Llama Guard 4 12B: 164K tokens; Nemotron 3.5 Content Safety: 131K tokens.

Where can I use both Llama Guard 4 12B and Nemotron 3.5 Content Safety?

deepinfra, edenai, fastrouter, kilo, nvidia, openrouter