{
  "page": "https://opencode.ai/data/vispark/vision-small",
  "updatedAt": null,
  "summary": "Vision Small costs $1.05 per 1M input tokens and $3.16 per 1M output tokens.",
  "model": {
    "id": "vispark/vision-small",
    "name": "Vision Small",
    "lab": "vispark",
    "labName": "Vispark",
    "family": null,
    "description": "Fast, low-cost multimodal model for understanding text, images, audio, video, and PDFs, with tool calling and a 1M-token context window.",
    "releaseDate": "2024-05-15",
    "lastUpdated": "2026-09",
    "knowledgeCutoff": null,
    "contextTokens": 1000000,
    "outputTokens": 65536,
    "inputModalities": [
      "text",
      "image",
      "audio",
      "video",
      "pdf"
    ],
    "outputModalities": [
      "text"
    ],
    "reasoning": true,
    "toolCall": true,
    "openWeights": false,
    "weights": [],
    "priceUsdPer1M": {
      "input": 1.05,
      "output": 3.16,
      "cachedInput": null,
      "cacheWrite": null
    },
    "benchmarks": []
  },
  "usage": null
}