{
  "page": "https://opencode.ai/data/microsoft/phi-4-multimodal-instruct",
  "updatedAt": null,
  "summary": "Phi-4-multimodal-instruct costs $0.00 per 1M input tokens and $0.00 per 1M output tokens.",
  "model": {
    "id": "microsoft/phi-4-multimodal-instruct",
    "name": "Phi-4-multimodal-instruct",
    "lab": "microsoft",
    "labName": "Microsoft",
    "family": "phi",
    "description": "Compact Microsoft multimodal model for text, image, and speech understanding",
    "releaseDate": "2025-02-26",
    "lastUpdated": "2025-02-26",
    "knowledgeCutoff": "2024-06",
    "contextTokens": 131072,
    "outputTokens": 131072,
    "inputModalities": [
      "text",
      "image",
      "audio"
    ],
    "outputModalities": [
      "text"
    ],
    "reasoning": false,
    "toolCall": true,
    "openWeights": true,
    "weights": [
      {
        "label": "Hugging Face",
        "url": "https://huggingface.co/microsoft/Phi-4-multimodal-instruct"
      }
    ],
    "priceUsdPer1M": {
      "input": 0,
      "output": 0,
      "cachedInput": null,
      "cacheWrite": null
    },
    "benchmarks": []
  },
  "usage": null
}