Nemotron 3 Ultra 550B A55B

NVIDIAOpen weights1.05M context

As of Oct 14, 2026, Nemotron 3 Ultra 550B A55B costs $0.60 per million input tokens and $2.40 per million output tokens from OpenRouter. The cheapest of 3 sellers is OpenRouter at $0.60 / $2.40.

Lowest price, from OpenRouter

Pricing page

Per million tokens

Input: $0.60
Output: $2.40
Cached input: $0.12
Batch input / output: —

Up to 183K output tokens per request.

Estimate your monthly cost

Input per month

M tokens

Output per month

M tokens

Input served from cache

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From OpenRouter: $10.80 a month.

Where to buy it (3)

Sorted by your monthly estimate. Prices per million tokens.

Seller	Input	Output	Cached input	Context	Est. per month10M in · 2M out
OpenRouterCheapest nvidia/nemotron-3-ultra-550b-a55b	$0.60	$2.40	$0.12	262K	$10.80
Together AI nvidia/nemotron-3-ultra-550b-a55b	$0.60	$3.60	$0.20	512K	$13.20
Nebius nebius/nvidia/Nemotron-3-Ultra-550b-a55b	$1.00	$3.00	—	1.05M	$16.00

OpenRouterCheapest
Input / output
$0.60 / $2.40
Context
262K
Per month
$10.80
nvidia/nemotron-3-ultra-550b-a55b
Together AI
Input / output
$0.60 / $3.60
Context
512K
Per month
$13.20
nvidia/nemotron-3-ultra-550b-a55b
Nebius
Input / output
$1.00 / $3.00
Context
1.05M
Per month
$16.00
nebius/nvidia/Nemotron-3-Ultra-550b-a55b

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Reasoning, Tool calling.

Lowest price, from OpenRouter

Estimate your monthly cost

Where to buy it (3)

Similar models