Nemotron 3 Super 120B A12B vs GLM-5.3: API price and specs

Nemotron 3 Super 120B A12B is 92% cheaper than GLM-5.3 on input price.

Nemotron 3 Super 120B A12B is 50% cheaper than GLM-5.3 on output price.

Nemotron 3 Super 120B A12B is 75% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.

Field	Nemotron 3 Super 120B A12B	GLM-5.3
Lowest input, per 1M	$0.015	$0.19 +1166%
Median input, per 1M	$0.11	$1.40 +1172.7%
Lowest output, per 1M	$0.32	$0.64 +100%
Median output, per 1M	$0.60	$4.40 +633.3%
Lowest unit price	—	$0.033 / request
Cost of 1M in + 200k out	$0.079	$0.32 +302.4%
Context	1M	1M
Max output	262K +75%	1M
Providers	20 +69.7%	66
Regions	EU, GLOBAL, US	APAC, EU, FI, GLOBAL, US
Accepts	file, text	file, image, text
Returns	text	text
Type	Text models	Text models
Free option	yes	yes
Cheapest provider	ollama-cloud	trustedrouter

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, amazon-bedrock, cloudflare-workers-ai, deepinfra, edenai, fastrouter, kenari, kilo, nebius, nvidia, ollama, ollama-cloud, opencode, openrouter, perplexity-agent, requesty, synthetic, trustedrouter, vercel

Frequently asked questions

Which is cheaper, Nemotron 3 Super 120B A12B or GLM-5.3?

Nemotron 3 Super 120B A12B is 92% cheaper than GLM-5.3 on input price. Nemotron 3 Super 120B A12B is 50% cheaper than GLM-5.3 on output price. Nemotron 3 Super 120B A12B is 75% cheaper than GLM-5.3 on a 1M-in / 200k-out workload.

Which has the larger context, Nemotron 3 Super 120B A12B or GLM-5.3?

Nemotron 3 Super 120B A12B: 1M tokens; GLM-5.3: 1M tokens.

Where can I use both Nemotron 3 Super 120B A12B and GLM-5.3?