{
  "key": "nemotron-3-ultra-550b",
  "name": "Nemotron 3 Ultra",
  "description": "Flagship Nemotron model for high-throughput reasoning and complex agents",
  "lab": "nvidia",
  "family": "nemotron",
  "release_date": "2026-06-04",
  "knowledge": null,
  "open_weights": false,
  "has_free_offering": false,
  "published": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": false,
    "tool_call": true,
    "structured_output": null,
    "attachment": false,
    "reasoning_options": null
  },
  "limit": {
    "context": 1048576,
    "output": 262144
  },
  "offerings": [
    {
      "provider": "digitalocean",
      "provider_model_id": "nemotron-3-ultra-550b",
      "name": "Nemotron 3 Ultra",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.9,
        "output": 1.7,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 131072,
        "input": null
      },
      "status": null,
      "last_updated": "2026-06-12"
    },
    {
      "provider": "llmgateway",
      "provider_model_id": "nemotron-3-ultra-550b",
      "name": "Nemotron 3 Ultra 550B A55B",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.5,
        "output": 2.2,
        "cache_read": 0.1,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1048576,
        "output": 128000,
        "input": null
      },
      "status": null,
      "last_updated": "2026-06-04"
    },
    {
      "provider": "llmgateway-providers",
      "provider_model_id": "deepinfra/nemotron-3-ultra-550b",
      "name": "Nemotron 3 Ultra 550B (DeepInfra)",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.5,
        "output": 2.2,
        "cache_read": 0.1,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 262144,
        "output": 262144,
        "input": null
      },
      "status": null,
      "last_updated": "2026-06-01"
    }
  ]
}