NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 vs Beam-1.0-501B-A23B

Specs, VRAM requirements and download trends — updated 25 October 2026.

nvidia · A · Open weights

Params

560.5 B

Context

262,144

30d

1.1 M

reflection · B · Open weights

Params

501.3 B

Context

1,048,576

30d

4 K

apache-2.0 · commercial OK

Specification comparison

Differences are highlighted; identical values are muted.

Specification	NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16	Beam-1.0-501B-A23B
Deployment	Open weights · also via API	Open weights · also via API
Parameters	560.5 B	501.3 B
Architecture	NemotronHForCausalLM	BeamForCausalLM
Context length	262,144	1,048,576
Licence	other	apache-2.0
Commercial use	Unknown	Allowed
Languages	12	1
Downloads 30d	1,133,423	4,432
Downloads all time	2.2 M	4 K
Quantizations on the Hub	SAFETENSORS	SAFETENSORS
Gated	No	No
First seen on the Hub	2026-06-03	2026-10-07
API input price / 1M tokens	$0.60	$0.25
API output price / 1M tokens	$2.40	$1.00
Est. cost per 1M input + 1M output tokens	$3.00	$1.25
Cached input / 1M tokens	$0.12	$0.05
AA Intelligence Index	22.9	—
AA Coding Index	49.3	—
AA Agentic Index	20.1	—
Max output tokens	182,520	131,072
API providers	3	6
Tool calling	Yes	Yes
Reasoning mode	Yes	Yes