{
  "key": "llama-3-3-nemotron-super-49b-v1-5",
  "name": "Llama 3.3 Nemotron Super 49B v1.5",
  "description": "Nemotron model for efficient reasoning, coding, and specialized AI agents",
  "lab": "nvidia",
  "family": "nemotron",
  "release_date": "2025-07-25",
  "knowledge": null,
  "open_weights": true,
  "has_free_offering": false,
  "published": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": true,
    "tool_call": true,
    "structured_output": null,
    "attachment": false,
    "reasoning_options": [
      {
        "type": "toggle"
      }
    ]
  },
  "limit": {
    "context": 131072,
    "output": 131072
  },
  "offerings": [
    {
      "provider": "deepinfra",
      "provider_model_id": "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5",
      "name": "Llama 3.3 Nemotron Super 49B v1.5",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.4,
        "output": 0.4,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 131072,
        "input": null
      },
      "status": "deprecated",
      "last_updated": "2025-07-25"
    },
    {
      "provider": "nvidia",
      "provider_model_id": "nvidia/llama-3.3-nemotron-super-49b-v1.5",
      "name": "Llama 3.3 Nemotron Super 49B v1.5",
      "variants": [],
      "free": false,
      "priced": false,
      "cost": {
        "input": 0,
        "output": 0,
        "cache_read": null,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 131072,
        "output": 65536,
        "input": null
      },
      "status": null,
      "last_updated": "2025-07-25"
    }
  ]
}