LLMNVIDIA Nemotron 3 Ultra API pricing
NVIDIA Nemotron 3 Ultra by Hyperbolic costs $0.50 per 1M input tokens and $2.20 per 1M output tokens (1M in + 1M out = $2.70).
- API model id
nemotron-3-ultra-550b-a55b- Input / 1M
- $0.50
- Output / 1M
- $2.20
- Cached input / 1M
- $0.10
- Context window
- 203K
- Notes
- Hyperbolic serverless inference (relaunched), USD per 1M tokens as of 2026-10-21, billed from prepaid credits. Requires a Pro plan (one-time $5+ deposit, no subscription) or an Organization.
- Source
- https://hyperbolic.ai/docs/inference/overview
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Docs and security page do not publish serving regions ('geographically distributed data centers'). Privacy policy: headquartered in the United States; personal data may be transferred to the US or other locations.
- Last verified
- 2026-10-26
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Hyperbolic | NVIDIA Nemotron 3 Ultra | $1.05 |
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 Hyperbolic models
- GLM-5.3 Flash: $0.15 / $0.50
- GLM-5.3: $1.40 / $4.40
- Kimi K3: $3.00 / $15.00
- MiniMax M3: $0.30 / $1.20
- DeepSeek V4.1 Flash: $0.30 / $1.20
- DeepSeek V4 Flash 0731: $0.06 / $0.18
- Step 5 Preview: $1.00 / $2.70
- MiMo-V2.6 Flash: $0.14 / $0.28