NVIDIA · live price
Nemotron 3 Ultra API pricing
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...
Small and cheap (under $1 per 1M)Tool callingReasoning
- Input
- $0.5
- per 1M tokens
- Output
- $2.20
- per 1M tokens
- Cached input
- $0.1
- per 1M tokens
- Context
- 262K
- 16K max output
List price from OpenRouter, which passes NVIDIA's price through without markup. Refreshed hourly. Released June 4, 2026. Model id nvidia/nemotron-3-ultra-550b-a55b.
What Nemotron 3 Ultra costs in practice
At list price, before any batch or caching discount.
1,000 chat messages
$1.60
1,000 input + 500 output tokens each
1,000 RAG questions
$5.10
8,000 input + 500 output tokens each
100 coding-agent steps
$1.94
30,000 input + 2,000 output tokens each, no caching
Nemotron 3 Ultra price history
Price last changed on 2026-11-17. We record prices daily since 2026-10-01.
Nemotron 3 Ultra price by host
DeepInfra serves it below list price right now. Route to it to pay less on every token.
- DeepInfra$0.4 in · $1.76 out · 262K ctx · 100.0% uptime 24h
- CoreWeave$0.5 in · $2.15 out · 262K ctx · 95.0% uptime 24h
- KT$0.5 in · $2.20 out · 262K ctx · 100.0% uptime 24h
- Fireworks$0.6 in · $2.40 out · 262K ctx · 97.3% uptime 24h
- BaseTen$0.6 in · $2.40 out · 203K ctx · 100.0% uptime 24h
- Venice$0.625 in · $3.13 out · 256K ctx · 99.0% uptime 24h
Where to buy NVIDIA credits for less
Nemotron 3 Ultra costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:
Nemotron 3 Ultra cost calculator
Enter your monthly tokens to price your own usage.
Usage at list price$47.00/ month
Cheaper alternatives to Nemotron 3 Ultra
Other labs' models in the same price range or the one below, cheaper per token.
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Z.ai: GLM 5.3 FlashX Legal | $0.37 | $1.25 |
| MiniMax: MiniMax M3.1 Flash | $0.15 | $0.6 |
| DeepSeek: DeepSeek V4.1 Flash 1017 | $0.15 | $0.6 |
| Anthropic: Claude Haiku 5.5 | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna Pro | $0.1 | $0.5 |
| OpenAI: GPT-6 Luna | $0.1 | $0.5 |
Other NVIDIA models
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Nemotron 3.5 Content Safety | $0.2 | $0.2 |
| Nemotron 3.5 Lightning | $0.07 | $0.2 |
| Nemotron 3 Super | $0.075 | $0.4 |
| Nemotron 3.5 Super VL | $0.15 | $0.47 |
| Nemotron 3 Nano 30B A3B | $0.06 | $0.24 |