NVIDIA Nemotron 3.5 Super VL vs GLM-5.2: API price and specs

NVIDIA Nemotron 3.5 Super VL is 65% cheaper than GLM-5.2 on input price.

NVIDIA Nemotron 3.5 Super VL is 35% cheaper than GLM-5.2 on output price.

NVIDIA Nemotron 3.5 Super VL is 53% cheaper than GLM-5.2 on a 1M-in / 200k-out workload.

Field	NVIDIA Nemotron 3.5 Super VL	GLM-5.2
Lowest input, per 1M	$0.06	$0.17 +183.3%
Median input, per 1M	$0.15	$1.40 +833.3%
Lowest output, per 1M	$0.35	$0.54 +54.3%
Median output, per 1M	$0.50	$4.40 +780%
Lowest unit price	—	$0.033 / request
Cost of 1M in + 200k out	$0.13	$0.28 +113.8%
Context	1M	1M
Max output	1M	1M
Providers	17 +71.2%	59
Regions	GLOBAL, US	APAC, EU, GLOBAL, US
Accepts	file, image, text, video	file, image, text
Returns	text	text
Type	Text models	Text models
Free option	yes	yes
Cheapest provider	kilo	edenai

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, aiml, baseten, deepinfra, digitalocean, edenai, fastrouter, io-net, kenari, kilo, nebius, opencode, openrouter, togetherai, trustedrouter, vercel

Frequently asked questions

Which is cheaper, NVIDIA Nemotron 3.5 Super VL or GLM-5.2?

NVIDIA Nemotron 3.5 Super VL is 65% cheaper than GLM-5.2 on input price. NVIDIA Nemotron 3.5 Super VL is 35% cheaper than GLM-5.2 on output price. NVIDIA Nemotron 3.5 Super VL is 53% cheaper than GLM-5.2 on a 1M-in / 200k-out workload.

Which has the larger context, NVIDIA Nemotron 3.5 Super VL or GLM-5.2?

NVIDIA Nemotron 3.5 Super VL: 1M tokens; GLM-5.2: 1M tokens.

Where can I use both NVIDIA Nemotron 3.5 Super VL and GLM-5.2?

aihubmix, aiml, baseten, deepinfra, digitalocean, edenai, fastrouter, io-net, kenari, kilo, nebius, opencode, openrouter, togetherai, trustedrouter, vercel