Nemotron 3 Ultra
$0.60 per 1M input tokens and $2.40 per 1M output tokens · 262K context · tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Nemotron 3 Ultra costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $314 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $67.68 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $144 |
| Content generation 30 long articles a day | $7.02 |
| Classification / extraction 100,000 short items a day | $648 |
Price history
We started tracking Nemotron 3 Ultra on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Nemotron 3 Ultra: 5 providers
DeepInfra is the cheapest at $0.40 input / $1.76 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
Cheaper alternatives to Nemotron 3 Ultra
Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| MiMo-V2.6-Pro Xiaomi | $0.435 | $0.87 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| GLM 5.3 Z.ai | $0.079 | $1.40 | 1.05M | toolsreasoningJSONopen weights |
| Claude Haiku 5.5 Anthropic | $0.10 | $0.50 | 1M | visiontoolsreasoningJSON |
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.1 Flash inclusionAI | $0.075 | $0.225 | 262K | toolsreasoningJSON |
How to pay less for Nemotron 3 Ultra
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $418 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to MiMo-V2.6-Pro (similar capabilities) | $136 | $281 (67%) |
| Route to DeepInfra (flex tier) | $292 | $126 (30%) |
| Use prompt caching (60% of input cached) | $314 | $104 (25%) |
Other workloads: cut-your-bill tool for Nemotron 3 Ultra.
Specifications
| Model ID | nvidia/nemotron-3-ultra-550b-a55b |
| Input | text |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 |
| Released | Jun 4, 2026 |
FAQ
- How much does Nemotron 3 Ultra cost?
- $0.60 per million input tokens and $2.40 per million output tokens; cached input costs $0.12 per million. Prices as of Oct 21, 2026.
- What is the context window of Nemotron 3 Ultra?
- 262K tokens, with up to 183K output tokens per response.
- Does Nemotron 3 Ultra support images, tools and structured output?
- Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to Nemotron 3 Ultra?
- Models with the same key capabilities for at least 20% less include MiMo-V2.6-Pro ($0.435 / $0.87), GLM 5.3 ($0.079 / $1.40), Claude Haiku 5.5 ($0.10 / $0.50).
More from NVIDIA: all NVIDIA models · how we collect prices