{
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-04",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.3",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "tool": {
    "author": "inception",
    "category": "inference",
    "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/mercury.json",
    "kind": "model",
    "listed": "indexed",
    "maker": "Inception",
    "markdownUrl": "https://www.anchorterminal.com/tools/mercury.md",
    "modelCount": 2,
    "models": [
      {
        "contextTokens": 260000,
        "id": "inception/mercury-2.5",
        "input": [
          "text"
        ],
        "inputUsdPerM": 0.04,
        "maxOutput": 65536,
        "name": "Mercury 2.5",
        "outputUsdPerM": 0.15,
        "promptCaching": true,
        "reasoning": true,
        "released": "2026-09-08",
        "structuredOutputs": true,
        "tools": true
      },
      {
        "contextTokens": 128000,
        "id": "inception/mercury-2",
        "input": [
          "text"
        ],
        "inputUsdPerM": 0.25,
        "maxOutput": 50000,
        "name": "Mercury 2",
        "outputUsdPerM": 0.75,
        "promptCaching": true,
        "reasoning": true,
        "released": "2026-03-04",
        "structuredOutputs": true,
        "tools": true
      }
    ],
    "name": "Mercury",
    "note": "Indexed from OpenRouter: facts and our own checks, not reviewed, so no score, grade or rank.",
    "pageJsonUrl": "https://www.anchorterminal.com/tools/mercury.json",
    "reviewed": false,
    "slug": "mercury",
    "source": "OpenRouter",
    "sourceUrl": "https://openrouter.ai/inception/mercury-2.5",
    "summary": "Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...",
    "updatedAt": "2026-09-08T18:28:57Z",
    "url": "https://www.anchorterminal.com/tools/mercury",
    "vendor": "Inception",
    "vendorUrl": "",
    "why": [
      "openrouter"
    ]
  }
}