NVIDIA Nemotron 3 Ultra API pricing
NVIDIA Nemotron 3 Ultra by CoreWeave costs $0.50 per 1M input tokens and $2.15 per 1M output tokens (1M in + 1M out = $2.65).
- API model id
NVIDIA Nemotron 3 Ultra- Input / 1M
- $0.50
- Output / 1M
- $2.15
- Cached input / 1M
- $0.10
- Context window
- —
- Notes
- CoreWeave Serverless Inference, USD per 1M tokens (Serverless Inference product page).
- Source
- https://www.coreweave.com/products/serverless-inference
- Provider type
- Cloud (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — The Serverless Inference page lists per-model prices but does not state serving regions. OpenRouter's provider list reports CoreWeave's datacenters as US.
- Last verified
- 2026-10-19
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| CoreWeave | NVIDIA Nemotron 3 Ultra | $1.04 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other CoreWeave models
- Reflection Beam 1.0: $1.00 / $3.00
- NVIDIA Nemotron 3.5 Super VL: $0.25 / $1.50
- DeepSeek V4.1-Flash: $0.20 / $0.65
- IBM Granite 4.2 8B: $0.10 / $0.15
- Z.AI GLM 5.3: $1.20 / $4.00
- Qwen3.8 27B: $0.40 / $3.00
- Z.AI GLM 5.3 Flash: $0.15 / $0.50
- DeepSeek V4-Pro-0813: $1.31 / $3.96