nvidia/nemotron-3-nano-30b-a3b
nvidia/nemotron-3-ultra-550b-a55b
nvidia/nemotron-3-ultra-550b-a55bTarifs · par million de tokens
Capacités
- Vision — Comprend les images et documents envoyés
- Outils — Peut appeler vos fonctions / outils
Estimez votre coût
Utiliser ce modèle
Créez un compte, rechargez en dinars et appelez-le avec votre clé :
from openai import OpenAI
client = OpenAI(
base_url="https://dzrouter.com/v1",
api_key="sk-dz-…",
)
reply = client.chat.completions.create(
model="nvidia/nemotron-3-ultra-550b-a55b",
messages=[{"role": "user", "content": "Salam!"}],
)
print(reply.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://dzrouter.com/v1",
apiKey: process.env.DZROUTER_API_KEY,
});
const reply = await client.chat.completions.create({
model: "nvidia/nemotron-3-ultra-550b-a55b",
messages: [{ role: "user", content: "Salam!" }],
});
console.log(reply.choices[0].message.content);curl https://dzrouter.com/v1/chat/completions \
-H "Authorization: Bearer $DZROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia/nemotron-3-ultra-550b-a55b",
"messages": [{"role": "user", "content": "Salam!"}],
"stream": true
}'from anthropic import Anthropic
client = Anthropic(
base_url="https://dzrouter.com",
api_key="sk-dz-…",
)
msg = client.messages.create(
model="nvidia/nemotron-3-ultra-550b-a55b",
max_tokens=1024,
messages=[{"role": "user", "content": "Salam!"}],
)
print(msg.content[0].text)Autres modèles NVIDIA
nvidia/nemotron-3-super-120b-a12b
nvidia/nemotron-3-120b
NVIDIA's hybrid MoE model with leading accuracy for multi-agent applications and specialized agentic AI systems.
nvidia/nemotron-3-nano-30b
NVIDIA's efficient hybrid MoE model combining Mamba-2 and Transformer layers, with 30B total and 3.5B active parameters. Reasoning can be toggled on or off, and it handles English, code and several European and Asian languages.
nvidia/nemotron-3-nano-omni
NVIDIA's compact multimodal Nemotron 3 Nano with 30B total / 3B active MoE parameters and built-in reasoning. Strong at agentic and analytical tasks.
nvidia/nemotron-3-ultra-nvfp4
NVIDIA's frontier-scale hybrid Latent-MoE model (550B total, 55B active) for the most demanding agentic, reasoning, and long-context workloads across code, math, and science. Trained with an NVFP4 recipe.
Commencez à construire avec l'IA dès aujourd'hui
Créez votre compte, rechargez dès 500 DA et envoyez votre première requête en quelques minutes.
Créer un compte gratuit