VILA

{
  "id": "vila",
  "object": "model",
  "created": null,
  "owned_by": "nvidia",
  "name": "VILA",
  "api": {
    "types": [
      "chat"
    ]
  },
  "limits": {
    "context": null,
    "input": null,
    "output": null
  },
  "modalities": {
    "input": [
      "text",
      "image",
      "video"
    ],
    "output": [
      "text"
    ]
  },
  "reasoning": {
    "supported": null,
    "efforts": []
  },
  "pricing": null,
  "features": [],
  "info": {
    "status": "active",
    "release_date": null,
    "knowledge_cutoff": null,
    "description": "Vision language model that queries and summarizes images and video from the physical or virtual world.",
    "docs": "https://docs.api.nvidia.com/nim/reference/nvidia-vila",
    "verified_at": "2026-10-11"
  }
}