modelsdev NVIDIA Nemotron 3 Ultra (venice/nvidia-nemotron-3-ultra-550b-a55b)
modelsdev NVIDIA Nemotron 3 Ultra costs USD 0.625 per 1M input tokens and USD 3.125 per 1M output tokens (community cross-check, https://models.dev/), verified 2026-10-24 17:47 UTC.
Last verified 2026-10-24T17:47:11+00:00 · Source: https://models.dev/ (community cross-check, waak source modelsdev)
A first-party listing of this model exists and is shown below; this row is the community cross-check.
Price
- Input
- USD 0.625 / 1M tokens
- Output
- USD 3.125 / 1M tokens
- Cached input
- USD 0.1875 / 1M
- This price since
- 2026-10-19T22:42:32+00:00
- FX used
- 1 EUR = 1.1225 USD (ECB)
- Billing
- per_token
Specification
- Context window (tokens)
- 256,000
- Max output
- 32,768
- Open weights
- yes
- Reasoning
- yes
- Source kind
- community
- Vendor
- venice
- Region
- global
- Listing
- listing not verifiable
aggregator / community mirror: no first-party public page to check against - First seen
- 2026-10-19T22:42:32+00:00
- SKU id
llm/modelsdev/venice/nvidia-nemotron-3-ultra-550b-a55b
Other listings of this model
Sources can disagree. The provider's own listing is first-party; LiteLLM, OpenRouter and models.dev are community cross-checks. Differences are shown, not resolved.
| SKU | Source | Input / 1M | Output / 1M | vs this page | Last verified |
|---|---|---|---|---|---|
| llm/deepinfra/nvidia/nvidia-nemotron-3-ultra-550b-a55b | deepinfra-models (first-party) | 0.50 | 2.20 | differs differs by -20.0% | 2026-10-24T17:47:11+00:00 |
| llm/modelsdev/baseten/nvidia/nvidia-nemotron-3-ultra-550b-a55b | modelsdev (community cross-check) | 0.60 | 2.40 | differs differs by -4.0% | 2026-10-24T17:47:11+00:00 |
| llm/modelsdev/wandb/nvidia/nvidia-nemotron-3-ultra-550b-a55b | modelsdev (community cross-check) | 0.50 | 2.15 | differs differs by -20.0% | 2026-10-24T17:47:11+00:00 |
| llm/baseten/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | litellm (community cross-check) | 0.60 | 2.40 | differs differs by -4.0% | 2026-10-24T17:01:34+00:00 |
| llm/deepinfra/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | litellm (community cross-check) | 0.50 | 2.20 | differs differs by -20.0% | 2026-10-24T17:01:34+00:00 |
| llm/wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B | litellm (community cross-check) | 0.50 | 2.15 | differs differs by -20.0% | 2026-10-24T17:01:34+00:00 |
Price history (90 days)
| Observed (UTC) | Price | USD | EUR | Output / 1M | Snapshot |
|---|---|---|---|---|---|
| 2026-10-19T22:42:32+00:00 | USD 0.625 | 0.625 | 0.5568 | 3.125 | #34 |
Each row is a change point: the price held from that moment until the next row. Full history: JSON · CSV.
Changes
No changes recorded since first seen.
API: /v1/skus/llm/modelsdev/venice/nvidia-nemotron-3-ultra-550b-a55b
Cite this
Free to reuse under CC BY 4.0 with this credit. The numbers are list prices, not transacted prices.
InfraRabbit (2026). modelsdev NVIDIA Nemotron 3 Ultra [data as of 2026-10-24]. https://infrarabbit.com/llm/modelsdev/venice/nvidia-nemotron-3-ultra-550b-a55b (accessed 2026-10-24). List prices, not transacted prices. CC BY 4.0.
BibTeX
@misc{infrarabbit_llm_modelsdev_venice_nvidia_nemotron_3_ultra_550b_a55b_2026,
author = {{InfraRabbit}},
title = {modelsdev NVIDIA Nemotron 3 Ultra},
year = {2026},
howpublished = {\url{https://infrarabbit.com/llm/modelsdev/venice/nvidia-nemotron-3-ultra-550b-a55b}},
note = {Data as of 2026-10-24; accessed 2026-10-24; list prices, not transacted prices; CC BY 4.0}
}