NVIDIA-Nemotron-3-Super-120B-A12B-BF16 vs Step-3.5-Flash

Specs, VRAM requirements and download trends — updated 24 October 2026.

nvidia · A · Open weights

Params

123.6 B

Context

262,144

30d

978 K

stepfun-ai · B · Open weights

Params

199.4 B

Context

262,144

30d

264 K

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Super-120B-A12B-BF16	Step-3.5-Flash
Deployment	Open weights	Open weights · also via API
Parameters	123.6 B	199.4 B
Architecture	NemotronHForCausalLM	Step3p5ForCausalLM
Context length	262,144	262,144
Licence	other	apache-2.0
Commercial use	Unknown	Allowed
Languages	7	—
Downloads 30d	978,022	264,309
Downloads all time	7.1 M	1.9 M
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-03-10	2026-02-01
API input price / 1M tokens	not on OpenRouter	$0.10
API output price / 1M tokens	not on OpenRouter	$0.30
Est. cost per 1M input + 1M output tokens	not on OpenRouter	$0.40
Cached input / 1M tokens	not on OpenRouter	—
AA Intelligence Index	not on OpenRouter	17
AA Coding Index	not on OpenRouter	—
AA Agentic Index	not on OpenRouter	—
Max output tokens	not on OpenRouter	65,536
API providers	not on OpenRouter	1
Tool calling	not on OpenRouter	Yes
Reasoning mode	not on OpenRouter	Yes