NVIDIA: Nemotron 3 Ultra API Pricing
NVIDIA: Nemotron 3 Ultra costs $0.600 per 1M input tokens and $2.40 per 1M output tokens (cache reads: $0.120). Context window: 262K. Prices verified 2026-10-21 · source
Alternatives to consider
92% cheaper with nearly identical quality (41.8 vs 38)
Cheapest nvidia model — 90% less per month
Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.
High adoption means battle-tested weights, more fine-tunes/quants, and faster bug fixes. View on HuggingFace →
From our own daily snapshot archive — independent of provider announcements.
Intelligence measures reasoning/knowledge/coding benchmarks. A high score with a low blended price = value pick; check the value chart to see where this model lands.
Token economics
| Token type | Price | vs base input |
|---|---|---|
| Standard input | $0.600 | — |
| Cache read | $0.120 | −80% |
| Output | $2.40 | — |
Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.
Higher effort = deeper thinking = more reasoning tokens billed as output.
What would NVIDIA: Nemotron 3 Ultra cost you per month?
| Workload | Requests/mo | Avg tokens (in/out) | Est. monthly cost |
|---|---|---|---|
| Light chatbot | 10,000 | 800 / 400 | $14.40 |
| Coding agent | 5,000 | 8,000 / 2,000 | $48.00 |
| RAG pipeline | 30,000 | 4,000 / 500 | $108.00 |
| Doc summarizer | 2,000 | 20,000 / 1,000 | $28.80 |
Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.
About NVIDIA: Nemotron 3 Ultra
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
Compare NVIDIA: Nemotron 3 Ultra with
- 3 Ultra vs OpenAI: GPT-5.6 Terra Pro
- 3 Ultra vs Anthropic: Claude Fable 5
- 3 Ultra vs Anthropic: Claude Opus 5
- 3 Ultra vs OpenAI: GPT-5.6 Sol
Popular head-to-heads — see all on the comparisons index.
Frequently asked questions
How much does NVIDIA: Nemotron 3 Ultra cost?
NVIDIA: Nemotron 3 Ultra costs $0.600 per 1M input tokens and $2.40 per 1M output tokens; cached input tokens cost $0.120 per 1M. Verified 2026-10-21 — provider source.
What is the context window?
262K tokens, with up to 183K output tokens per response. That's roughly 328 pages of text in a single request.
Does it support prompt caching?
Yes — cached input is $0.120/1M, about 80% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.
What's a cheaper alternative?
ScaleDown: Summarize saves about 97% on a typical workload with comparable quality.
Official resources
- NVIDIA: Nemotron 3 Ultra on OpenRouter — live endpoint, pricing source of record.
- Artificial Analysis benchmarks → — independent intelligence and performance analysis.
- Shred your current bill — paste a CSV and see if switching saves money.