On this page

Pricing Calculator Self-hosting GPUs Capabilities Benchmarks FAQ Cite

Layers / 03 Model / Foundation / LLMs / nvidia/nemotron-3-ultra-550b-a55b:free

nvidia/nemotron-3-ultra-550b-a55b:free

○ params1M context○ cutoff○ released○ licence

Aa

Compare vs similar

nvidia/nemotron-3-ultra-550b-a55b:free costs $0 / $0 per 1M tokens in/out at the cheapest of 1 seller.

Cheapest: OpenRouter · read 2026-10-27 ↗

Hosted pricing — 1 seller, cheapest first

The cheapest hosted rate is $0 in / $0 out at OpenRouter. Every row cites the pricing page it was read from.

SellerInput ↓OutputCached inBatchRead

OpenRouter$0$0○○2026-10-27 ↗

Cost calculator

INPUT TOKENS / MO120M

OUTPUT TOKENS / MO40M

CACHED SHARE OF INPUT0%

Sellers without a cached tier bill it at full input rate

OpenRouter$0 /mo

Compare against another model →

Self-hosting — what it takes to run

QuantMemoryCheapest GPU that fitsEst $/mo 24/7

4-bit○○○
8-bit○○○
16-bit○○○

memory needs the model's parameter count and weights size · no seller publishes either to us · rates live from /gpu

GPUs that can run this model

Live cheapest rates · from /gpu

B300-SXM-288GB →○ · ~288 GB$4.00/hr GB300-SXM-288GB →○ · ~288 GB$12.67/hr MI325X-256GB →○ · ~256 GB$3.80/hr B200-SXM-192GB →○ · ~192 GB$3.74/hr MI300X-192GB →○ · ~192 GB$2.39/hr

each row links to that GPU’s live price table · whether this model fits is not computed, because weights and KV cache are figures we do not hold

Capabilities

Function calling○ no answer on record

Structured JSON output○ no answer on record

Vision input✕

Audio input✕

Fine-tuning API○ no answer on record

System prompt○ no answer on record

Benchmarks

⚑ Creator-reported — not independently reproduced

MMLU-Pro○
GPQA Diamond○
HumanEval○
MATH-500○
MMMU (vision)○
SWE-bench○

Full benchmark + price comparison →

A ring means nobody has told us · we run no evaluations of our own

Vs its class

In-category only · other NVIDIA models we price

ModelIn/Out $/1MContextFunction calls

nvidia/nemotron-3-nano-30b-a3b$0.05 / $0.2262K○
nvidia/nemotron-3.5-lightning$0.07 / $0.2262K○
nvidia/nemotron-3.5-content-safety$0.2 / $0.2131K○
nvidia/nemotron-3.5-super-vl$0.15 / $0.51M○
nvidia/nemotron-3-super-120b-a12b$0.3 / $2.4262K○

Often compared against

Which other models readers put beside this one on a compare page · last 30 days

Nobody has compared this model against another in the last 30 days.

Cite this page

infratoapp, “nvidia/nemotron-3-ultra-550b-a55b:free — hosted pricing across 1 seller”, read 27 October 2026. $0 input / $0 output per million tokens at OpenRouter. https://www.infratoapp.com/llm-prices/nvidia--nemotron-3-ultra-550b-a55b_free

Reading date travels inside the citation. How we read this data →