AI Rate Card

Nemotron 3 Ultra 550B A55B · requesty

Nemotron-3-Ultra-550B-A55B-NVFP4 is a frontier-scale large language model (LLM) trained by NVIDIA, designed to deliver strong agentic, reasoning, and conversational capabilities. It is optimized for the most demanding workloads, including complex multi-step agents, long-context analysis, and high-accuracy reasoning over code, math, and science. The model employs a hybrid Latent Mixture-of-Experts (LatentMoE) architecture, utilizing interleaved Mamba-2 and MoE layers, along with select Attention layers. Like the Super model, the Ultra model incorporates Multi-Token Prediction (MTP) layers for faster text generation and improved quality, and it is trained using an NVFP4 pre-training recipe to maximize compute efficiency. The model has 55B active parameters and 550B parameters in total.

Modèle de baseTous les modèles de cette baseTous les modèles du fournisseurvers le fournisseur

Tous les modèles NVIDIA chez tous les fournisseurs

Entrée, $/1M $0.60

Sortie, $/1M $2.40

Lecture cache $0.12

Écriture cache —

Contexte 262 144

Sortie max. 262 144

Accepte texte

Dernière vérification 04.11.2026 12:00:14 UTC

Source page du fournisseur

Alertes de prix

Connectez-vous pour suivre le prix

API

API compatible OpenAI : les SDK officiels d'OpenAI fonctionnent avec cette URL de base. Remplacez YOUR_API_KEY par votre clé du fournisseur.

URL de base de l'API
https://router.requesty.ai/v1
Point de terminaison
https://router.requesty.ai/v1/chat/completions
ID du modèle
fireworks/nemotron-3-ultra-nvfp4
curl
curl https://router.requesty.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "fireworks/nemotron-3-ultra-nvfp4", "messages": [{"role": "user", "content": "Hello!"}], "max_tokens": 256}'
Python
import requests

r = requests.post(
    "https://router.requesty.ai/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "model": "fireworks/nemotron-3-ultra-nvfp4",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ],
      "max_tokens": 256
    },
)
print(r.json())
JavaScript
const r = await fetch("https://router.requesty.ai/v1/chat/completions", {
  method: "POST",
  headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
  body: JSON.stringify({
    "model": "fireworks/nemotron-3-ultra-nvfp4",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "max_tokens": 256
  }),
});
console.log(await r.json());
Requête (JSON)
{
  "model": "fireworks/nemotron-3-ultra-nvfp4",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 256
}
Réponse (JSON)
{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "fireworks/nemotron-3-ultra-nvfp4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! How can I help?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

L'adresse provient de la liste de modèles du fournisseur ; vérifiez-la dans sa documentation.

Documentation API du fournisseur

Source: AI Rate Card, https://airatecard.com/fr/c/offer%3Arequesty%7Cfireworks/nemotron-3-ultra-nvfp4, prices checked 2026-11-04; seller's page: https://www.requesty.ai/models/fireworks/nemotron-3-ultra-nvfp4

Détails techniques

ID: offer:requesty|fireworks/nemotron-3-ultra-nvfp4