Back to Models

Llama Nemotron Ultra

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA
15/ 57

Intelligence Score

Intelligence

15

#151 of 212 (top 71%)

Speed

41 tok/s

#127 of 141

Price

$0.90

per M tokens

#80 cheapest of 142

Context Window

128K

tokens

Latency: 3ms (#99)

Score Breakdown

Quality Score25%
Speed Score5%
Cost Score92%

Similar Models

Step3 VL 10B

![StepFun](https://artificialanalysis.ai/img/logos/stepfun_small.svg)StepFun

15intelligence

Gemma 4 E2B

![Google](https://artificialanalysis.ai/img/logos/google_small.svg)Google

15intelligence

ERNIE 4.5 300B A47B

![Baidu](https://artificialanalysis.ai/img/logos/baidu_small.svg)Baidu

15intelligence

Solar Pro 2

![Upstage](https://artificialanalysis.ai/img/logos/upstage_small.svg)Upstage

15intelligence

NVIDIA Nemotron Nano 12B v2 VL

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA

15intelligence

Use This Model

Claude Code

claude --model llama-3-1-nemotron-ultra-253b-v1-reasoning

API (cURL)

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{
    "model": "llama-3-1-nemotron-ultra-253b-v1-reasoning",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("llama-3-1-nemotron-ultra-253b-v1-reasoning"),
  prompt: "Hello",
});
Back to Models