Evidence row 3754977

What was observed

{
  "count": 5,
  "tools": [
    {
      "description": "Rank models by monthly cost for a workload. Use a preset (chatbot, rag, coding_agent, research_agent) or give token numbers.",
      "inputSchema": {
        "properties": {
          "cached_percent": {
            "description": "Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)",
            "type": "number"
          },
          "calls_per_day": {
            "description": "Calls (or agent tasks) per day",
            "type": "number"
          },
          "input_tokens": {
            "description": "Input tokens per call/step",
            "type": "number"
          },
          "limit": {
            "description": "How many to return (default 5, max 20)",
            "type": "number"
          },
          "output_tokens": {
            "description": "Output tokens per call/step",
            "type": "number"
          },
          "popular_only": {
            "description": "Only well-known models (default true)",
            "type": "boolean"
          },
          "preset": {
            "description": "Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it.",
            "enum": [
              "chatbot",
              "rag",
              "coding_agent",
              "research_agent"
            ],
            "type": "string"
          },
          "steps_per_task": {
            "description": "Model calls per task for multi-step agents (default 1)",
            "type": "number"
          }
        },
        "type": "object"
      },
      "name": "cheapest_models_for"
    },
    {
      "description": "Compare 2-5 models on price and (optionally) on the monthly cost of one workload.",
      "inputSchema": {
        "properties": {
          "cached_percent": {
            "description": "Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)",
            "type": "number"
          },
          "calls_per_day": {
            "description": "Calls (or agent tasks) per day",
            "type": "number"
          },
          "input_tokens": {
            "description": "Input tokens per call/step",
            "type": "number"
          },
          "models": {
            "items": {
              "type": "string"
            },
            "maxItems": 5,
            "minItems": 2,
            "type": "array"
          },
          "output_tokens": {
            "description": "Output tokens per call/step",
            "type": "number"
          },
          "preset": {
            "description": "Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it.",
            "enum": [
              "chatbot",
              "rag",
              "coding_agent",
              "research_agent"
            ],
            "type": "string"
          },
          "steps_per_task": {
            "description": "Model calls per task for multi-step agents (default 1)",
            "type": "number"
          }
        },
        "required": [
          "models"
        ],
        "type": "object"
      },
      "name": "compare_models"
    },
    {
      "description": "Estimate the monthly API cost of an AI agent or chatbot on one model. Easiest: pass model + preset (chatbot, rag, coding_agent, research_agent). Or give input_tokens, output_tokens and calls_per_day (plus optional steps_per_task, cached_percent); explicit numbers override the preset.",
      "inputSchema": {
        "properties": {
          "cached_percent": {
            "description": "Share of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)",
            "type": "number"
          },
          "calls_per_day": {
            "description": "Calls (or agent tasks) per day",
            "type": "number"
          },
          "input_tokens": {
            "description": "Input tokens per call/step",
            "type": "number"
          },
          "model": {
            "description": "Model id like anthropic/claude-sonnet-5.5, or a name like \"Grok 4.7\"",
            "type": "string"
          },
          "output_tokens": {
            "description": "Output tokens per call/step",
            "type": "number"
          },
          "preset": {
            "description": "Optional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it.",
            "enum": [
              "chatbot",
              "rag",
              "coding_agent",
              "research_agent"
            ],
            "type": "string"
          },
          "steps_per_task": {
            "description": "Model calls per task for multi-step agents (default 1)",
            "type": "number"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "estimate_cost"
    },
    {
      "description": "API list price of one model (input, output, cached input per 1M tokens) plus example monthly agent costs. For retired models, rates are last recorded list prices (see pricing_basis/recorded_note).",
      "inputSchema": {
        "properties": {
          "model": {
            "description": "Model id like anthropic/claude-sonnet-5.5, or a name",
            "type": "string"
          }
        },
        "required": [
          "model"
        ],
        "type": "object"
      },
      "name": "get_model_price"
    },
    {
      "description": "List LLMs tracked by Agent Cost Hub with API list prices per 1M tokens. Optional filter by provider or text.",
      "inputSchema": {
        "properties": {
          "popular_only": {
            "type": "boolean"
          },
          "provider": {
            "description": "e.g. openai, anthropic, google",
            "type": "string"
          },
          "search": {
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_models"
    }
  ]
}

What the leaf hashes

{"body":"42fc6ba5c5144ba689e7b9cb1ddb65933e3f2507b89daaba7a39ee36224a975d","id":3754977,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793989511336747,"prev":2158287,"subject":"cb26523a-21df-4f20-ac43-075b52e7129e","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-11-06 (303443 rows).

1. 0x1fbdd08e79dd22b243a4750d3c962491f5080bf27ccf1895f0d86e88bf4ce8f8
2. 0xd7c0b584a13912575c8b3e19ba445e4a6bdbe6d83167af64980700a4320a863c
3. 0x1678eb5ab193b0e5811522e765b4be641d018271f5ff425555b6f5b65adada2c
4. 0x3dc4b98a73103f282b3ff0b76d77b94908acaaf9f2ceabab9d5089d5c0561355
5. 0xc8be958b96e18fb92d88f008cfe148071f6bebb12369bf50d972c47dab57ce9f
6. 0x93604618c75f46f6be77a7f8cee10bf0a4c5f770126bea47e0d0c13cfb1dc9e8
7. 0x7c36e62a2aedd1db5ad41809ccc022baeeb36212bf3d303cdc005f253efb6ec6
8. 0xe12eee7f5ce5ca695ca8d14fe53ce16f54e1787f403877e00fd5a5c5753c2bfa
9. 0x6a96281361a19183483e176a3b482487d31b63986f2db7258527a385390eeefd
10. 0xb176cbaf16a314b9bbfe87df303b3c75b0525b7158dc0e40e71e6e036b500ff2
11. 0x2a675834c10cf17c0789cdeb0a7d34aff9ad85da5332d478cc4122294bd7146f
12. 0x2712d96bbc03cfe1d2563129cc6e8172c8f1f652986a5baa01c71ea12986915c
13. 0xb4c69343b22f2d7ab818464af79dc568e8aa4fc1673ee1f934d83014bdf8d32a
14. 0x81d6ec63cb4df174d42a42d72162141e82dcafa9c256793b20cc12205d8d389c
15. 0xb490b9bc961e5cbbfaf890e393a2eb3d2518e080e0a107acd232486f34cf7408
16. 0x0aaf291a2ffa2205e7df7531bf36800e377dfbd67208da05b97625f1cc49ce02
17. 0xa448dc698494f795f2240c0e7070e8a93eb263baee21ca4185a7d03432a614d8
18. 0x119743aadcddb571b28b442b62196d4a0afc4e1c9979c2d477d34fcc9413deaf
19. 0xc0d08d48601d1be90bcfc025e66bcaa0030120d688dd9c919b36c2c4446f4948

Day root

0xb30ccefe7182c6f767e1fcbfb5f64ffd649da831f665f65c5ff39cd40512284f

Chained

0xc383f7ef68d2914082484765aa09e42c12c59a74a096ae64127c562618c506d3

Published

On Arc Testnet, block 71111178: 0xfba13cb7ee4ada7f2fee3702a786a2201596be2ffea37dfc281ab4c8e9942fe1