AI Rate CardBase model
Llama 3.1 Nemotron Ultra 253B
from $0.50 at 2 providers · free option
nvidia/llama-3.1-nemotron-ultra-253b · 253B parameters · 2 providers · Text models ·
Price alerts
Found 2
Simple Full
Ranges in one field: "from-to" - "0.5-3", "-3" (up to), "128k-" (from); a colon works too. Several ticked values of one column are ORed, columns are ANDed.
Input price history, $/1M
Latest: minimum $0.50, median $0.50 (Nov 4, 2026)
The NEMOTRON family - base models: 49
- nemotron
- Llama 3.1 Nemotron 70B Instruct 4
- Llama 3.1 Nemotron Nano 8B v1 1
- Llama 3.1 Nemotron Nano VL 8B v1 1
- Llama 3.1 Nemotron Safety Guard 8B v3 1
- Llama 3.1 Nemotron Ultra 253B 2
- Llama 3.3 Nemotron Super 49B v1 1
- Llama 3.3 Nemotron Super 49B v1.5 4
- Llama Nemotron Embed VL 1B v2 2
- Llama Nemotron Rerank VL 1B v2 2
- Mistral Nemotron 2
- nemotron-3.5-bolt-e4b 2
- nemotron-3.5-embed-1b 2
- nemotron-3.5-embed-8b 2
- Nemotron 3.5 Lightning 30B 1
- Nemotron 3.5 Lightning 30B Free cached input until Oct 31, 2026, 11:59 PM UTC 1
- Nemotron-3.5-Rerank-8B-BF16 1
- NVIDIA-Nemotron-3.5-Transcribe-30B-A4B 1
- nemotron-3-120b-a12b 2
- Nemotron 3 Content Safety 1
- Nemotron-3-Diarization-preview 2
- Nemotron 3 Embed 1B 2
- Nemotron-3-Embed-8B 1
- nemotron-3-nano 2
- Nemotron 3 Nano 30B A3B 18
- Nemotron 3 Nano Omni 30B A3B Reasoning 13
- Nemotron 3 Super 120B A12B 22
- Nemotron 3 Ultra 550B A55B 25
- Nemotron 3.5 ASR Streaming Multilingual 0.6B 1
- Nemotron 3.5 Content Safety 12
- Nemotron 3.5 Lightning 30B A3B 20
- Nemotron 3.5 Super 120B A12B 1
- NVIDIA Nemotron 3.5 Super VL 18
- Nemotron 3.5 Super VL 120B A12B 3
- nemotron-4-340b-instruct 2
- nemotron-4-340b-reward 1
- Nemotron-120B-A12B 1
- Nemotron Content Safety Reasoning 4B 1
- Nemotron Mini 4B Instruct 1
- nemotron-nano-3-30b-a3b 1
- Nemotron Nano 3 Omni 1
- Nemotron Nano 9B v2 7
- nvidia.nemotron-nano-12b-v2@us 2
- nemotron-nano-12b-v2 1
- Nemotron Nano 12B v2 VL 6
- nemotron-nano-v2-12b 1
- nemotron-parse 1
- nemotron-parse-2.0 1
- Nemotron-SEA-LION-v4.8-120B-A12B 1
- Nemotron VoiceChat 1
About the model: cost of your workload, questions, comparisons, citation
Cost of my workload → in the Tools tab: every provider of this model, cheapest first
Frequently asked questions
How much does Llama 3.1 Nemotron Ultra 253B API cost?
From $0.50 input and $0.50 output per 1M tokens, at aihubmix.
Which provider offers Llama 3.1 Nemotron Ultra 253B cheapest?
aihubmix offers the lowest price, $0.50 per 1M tokens, among 2 providers.
What is the context window of Llama 3.1 Nemotron Ultra 253B?
128K tokens.
Is there a free way to use Llama 3.1 Nemotron Ultra 253B?
Yes, free at: nvidia.
Compare
Source: AI Rate Card, https://airatecard.com/en/model/nvidia/llama-3.1-nemotron-ultra-253b, prices checked 2026-11-04