{
  "page": "https://opencode.ai/data/google/gemini-4-hydrogen",
  "updatedAt": null,
  "summary": "Gemini 4 Hydrogen costs $1.50 per 1M input tokens and $7.50 per 1M output tokens.",
  "model": {
    "id": "google/gemini-4-hydrogen",
    "name": "Gemini 4 Hydrogen",
    "lab": "google",
    "labName": "Google",
    "family": "gemini",
    "description": "Google's Gemini 4 model for everyday coding and agentic workflows, with four thinking levels and a 1M-token context window",
    "releaseDate": "2026-11-12",
    "lastUpdated": "2026-11-12",
    "knowledgeCutoff": "2026-03",
    "contextTokens": 1048576,
    "outputTokens": 65536,
    "inputModalities": [
      "text",
      "image",
      "video",
      "audio",
      "pdf"
    ],
    "outputModalities": [
      "text"
    ],
    "reasoning": true,
    "toolCall": true,
    "openWeights": false,
    "weights": [],
    "priceUsdPer1M": {
      "input": 1.5,
      "output": 7.5,
      "cachedInput": 0.075,
      "cacheWrite": null
    },
    "benchmarks": [
      {
        "name": "SWE-sweep",
        "score": 13.5,
        "metric": "%",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "Terminal-Bench",
        "score": 57,
        "metric": "cheating-adjusted",
        "version": "4.1",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "Agents' Last Exam",
        "score": 71.6,
        "metric": "score",
        "version": "1.1",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "AutomationBench-AA",
        "score": 76.1,
        "metric": "%",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "Vending-Bench",
        "score": 14549,
        "metric": "bank balance (USD)",
        "version": "2",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "OSWorld",
        "score": 77.6,
        "metric": "offline subset",
        "version": "2.1",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "MKA",
        "score": 53.4,
        "metric": "Climb WSR accuracy",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "Chartography",
        "score": 66.6,
        "metric": "%",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "Terminal-Bench-Science",
        "score": 51.4,
        "metric": "%",
        "version": "0.1",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      },
      {
        "name": "HLE-Diamond",
        "score": 58.8,
        "metric": "%",
        "source": "https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-hydrogen/"
      }
    ]
  },
  "usage": null
}