← All models
Balanced — strong quality at a mid priceOpen Weights
Nemotron 3 Ultra (batch) Pricing
NVIDIA · nvidia-nemotron-3-ultra-550b-a55b-batch
Input / 1M tokens
$0.300
Output / 1M tokens
$1.80
Context window
512,288 tokens
≈ 683 pages of text
Max output
—
What it costs in practice
Typical request (1,200 in + 400 out tokens)$0.0011
1,000 requests / month$1.08/mo10,000 requests / month$10.80/mo100,000 requests / month$108.00/moEstimate your own workloadOpens the calculator with Nemotron 3 Ultra (batch) preloaded — adjust volume and token counts there.
Price history
Only one price point recorded so far.
The staircase chart appears once a price change is detected.
What it excels at
Handles extended contexts up to 512k tokens; suited for batch workloads with low input pricing.
The business tradeoff
Open-weights deployment requires user-managed infrastructure; output token cost is six times input rate.
Cheaper from NVIDIA
Head-to-head
Vendor list rates, as of Aug 6, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.