Evidence row 569625

What was observed

{
  "count": 11,
  "tools": [
    {
      "description": "The same model, or a whole family, priced across every vendor that sells it: cheapest and highest offer, vendor count and spread ratio for each direction, plus each offer with its channel. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).\n\nExamples:\n  - \"Cheapest place to run Llama 3.3 70B\" -> model_name=\"Llama 3.3 70B\"\n  - \"Qwen family output prices\" -> model_family=\"Qwen\", direction=\"Output\"",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "direction": {
            "description": "Pricing direction",
            "enum": [
              "Input",
              "Output",
              "Cached Input"
            ],
            "type": "string"
          },
          "limit": {
            "default": 50,
            "description": "Maximum SKUs (default 50)",
            "maximum": 200,
            "minimum": 1,
            "type": "integer"
          },
          "model_family": {
            "description": "Whole family instead of one model, e.g. 'Llama', 'Qwen'",
            "type": "string"
          },
          "model_name": {
            "description": "Model to compare, e.g. 'GPT-4o', 'Llama 3.3 70B', 'DeepSeek V3'",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "compare_prices"
    },
    {
      "description": "The Attic Standard price indexes for AI inference: every published index at the week the site shows.\n\nSix families: Modality (text, multimodal, image, video, audio, voice, embeddings), Channel (model developers, cloud marketplaces, inference platforms, neoclouds), Tier (flagship, core, compact), License (open weights, restricted weights, proprietary), Origin (United States, China) and Use case (reasoning, coding).\n\nFor each index and direction (input, cached input, output) it returns the benchmark level (May 2026 = 100) with week, month and vs-base changes, the spot price (median, p25, p75 in dollars) with its own week, month and vs-base changes, and coverage counts with the May 2026 basket size, flagged where the basket has changed materially since the base.\n\nFree: fully public, the same figures atticstandard.com publishes. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).\n\nExamples:\n  - \"Where is text inference priced this week?\" -> index_code=\"TXT\"\n  - \"Compare the four channels\" -> index_category=\"Channel\"\n  - \"Open-weight versus proprietary\" -> index_category=\"License\"",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "index_category": {
            "description": "Index family: 'Modality', 'Channel', 'Tier', 'License', 'Origin', 'Use case'.",
            "type": "string"
          },
          "index_code": {
            "description": "One index, e.g. 'TXT', 'NCL', 'FLG' or the full code 'AIPI TXT GLB'. Omit for all published indexes.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "get_index_benchmarks"
    },
    {
      "description": "What sits inside an index basket this week. Free tier: the composition (SKUs, models and vendors, split by channel, origin, tier and license). Attic Standard MCP PRO: the model-by-model basket with the vendors selling each model.\n\nExamples:\n  - \"What is in the flagship index?\" -> index_code=\"FLG\"\n  - \"How much of the China index is sold through neoclouds?\" -> index_code=\"CHN\"",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "direction": {
            "description": "Limit to one pricing direction",
            "enum": [
              "Input",
              "Cached Input",
              "Output"
            ],
            "type": "string"
          },
          "index_code": {
            "description": "Index to open, e.g. 'TXT', 'FLG', 'CHN' or 'AIPI TXT GLB'",
            "type": "string"
          }
        },
        "required": [
          "index_code"
        ],
        "type": "object"
      },
      "name": "get_index_constituents"
    },
    {
      "description": "The nine market KPIs Attic Standard publishes each week.\n- Price structure: output premium, caching discount, caching availability\n- Price dynamics: repricing activity, repricing depth, post-launch drift\n- Competition: multi-vendor spread, first-party premium, marketplace premium\n\nEach KPI returns its value, interquartile range, population, week, month and vs-base changes, and its published definition. Free: fully public, the same figures atticstandard.com publishes.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "group": {
            "description": "Optional group: 'Price structure', 'Price dynamics' or 'Competition'",
            "type": "string"
          },
          "weeks": {
            "default": 1,
            "description": "Weeks of history per KPI (default 1, latest only)",
            "maximum": 52,
            "minimum": 1,
            "type": "integer"
          }
        },
        "type": "object"
      },
      "name": "get_kpis"
    },
    {
      "description": "Coverage of the tracked market (vendors and pricing services, in total, by channel and in published indexes; countries, models, priced SKUs, published indexes) and price distributions split by modality, unit and direction. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "modality": {
            "description": "Optional modality: Text, Multimodal, Image, Video, Audio, Voice",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "get_market_stats"
    },
    {
      "description": "One model in depth: specs (creator, origin, tier, license, context window, output limit, training cutoff, modalities), the Attic Standard indexes it belongs to, and its price at every vendor. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "model_name": {
            "description": "Model to look up, e.g. 'GPT-4o', 'Claude Sonnet 4.5', 'Llama 3.3 70B'",
            "type": "string"
          }
        },
        "required": [
          "model_name"
        ],
        "type": "object"
      },
      "name": "get_model_detail"
    },
    {
      "description": "Six capability and coverage measures drawn from the metadata behind every tracked model: reasoning tier share, long-context saturation, frontier context ceiling, output ceiling spread, training cutoff lag and vendor modality breadth. Read alongside the market KPIs, they explain why models are priced the way they are. Free: fully public, the same figures atticstandard.com publishes.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "get_model_intelligence"
    },
    {
      "description": "Weekly history. With index_code: the index series (benchmark level, May 2026 = 100, and the spot price with its 25th and 75th percentiles) for up to 260 weeks; free. With model_name: every vendor's price for that model week by week, showing when each SKU was repriced; Attic Standard MCP PRO.\n\nToken prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).\n\nExamples:\n  - \"How has the neocloud index moved since May?\" -> index_code=\"NCL\"\n  - \"Has anyone cut the price of DeepSeek V3 this quarter?\" -> model_name=\"DeepSeek V3\", weeks=13",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "direction": {
            "description": "Pricing direction",
            "enum": [
              "Input",
              "Cached Input",
              "Output"
            ],
            "type": "string"
          },
          "index_code": {
            "description": "Index history, e.g. 'TXT', 'DEV', 'OSS' or 'AIPI TXT GLB'. Free.",
            "type": "string"
          },
          "model_name": {
            "description": "Model price history across every vendor that sells it, e.g. 'GPT-4o'. PRO.",
            "type": "string"
          },
          "vendor": {
            "description": "With model_name: limit to one vendor. PRO.",
            "type": "string"
          },
          "weeks": {
            "default": 26,
            "description": "How many weeks back (default 26)",
            "maximum": 260,
            "minimum": 1,
            "type": "integer"
          }
        },
        "type": "object"
      },
      "name": "get_price_history"
    },
    {
      "description": "Everything one vendor sells: channel, country, pricing page, model and SKU counts, and the full price list. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "direction": {
            "description": "Optional pricing direction",
            "enum": [
              "Input",
              "Output",
              "Cached Input"
            ],
            "type": "string"
          },
          "limit": {
            "default": 100,
            "description": "Maximum SKUs (default 100)",
            "maximum": 500,
            "minimum": 1,
            "type": "integer"
          },
          "modality": {
            "description": "Optional modality: Text, Multimodal, Image, Video, Audio, Voice",
            "type": "string"
          },
          "vendor": {
            "description": "Vendor name or id, as listed by list_vendors",
            "type": "string"
          }
        },
        "required": [
          "vendor"
        ],
        "type": "object"
      },
      "name": "get_vendor_catalog"
    },
    {
      "description": "Every pricing service in the Attic Standard fleet, with its vendor (the company, in parent), channel (model developer, cloud marketplace, inference platform or neocloud), country, region, currency and pricing page. Returns the vendor and pricing-service totals. Filter by channel, region or country.",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "channel": {
            "description": "Optional channel: 'Model developer' (DEV), 'Cloud marketplace' (CLD), 'Inference platform' (PLT), 'Neocloud' (NCL)",
            "type": "string"
          },
          "country": {
            "description": "Optional country, e.g. 'United States', 'China', 'France'",
            "type": "string"
          },
          "region": {
            "description": "Optional region, e.g. 'North America', 'Europe', 'Asia'",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "list_vendors"
    },
    {
      "description": "Search every priced SKU by modality, vendor, channel, creator, family, tier, license, origin, reasoning, open weights, direction, maximum price and minimum context window. Cheapest first. Free tier returns counts, ranges and redacted samples; Attic Standard MCP PRO ($500/month, https://atticstandard.com/mcp) returns vendor names, model names and exact prices. Token prices are per 1,000 tokens; other modalities use their own unit (per image, per second, per minute, per 1,000 characters).\n\nExamples:\n  - \"Open-weight text models under $0.0005 per 1,000 output tokens\" -> open_source=\"true\", modality=\"Text\", direction=\"Output\", max_price=0.0005\n  - \"Chinese reasoning models on neoclouds\" -> origin=\"China\", reasoning=\"true\", channel=\"Neocloud\"",
      "inputSchema": {
        "$schema": "http://json-schema.org/draft-07/schema#",
        "additionalProperties": false,
        "properties": {
          "_atom_api_key": {
            "description": "Your Attic Standard MCP PRO key for vendor- and SKU-level data. Omit for the free tier.",
            "type": "string"
          },
          "channel": {
            "description": "'Model developer', 'Cloud marketplace', 'Inference platform' or 'Neocloud'",
            "type": "string"
          },
          "creator": {
            "description": "Model creator (the lab that built the model)",
            "type": "string"
          },
          "direction": {
            "description": "Pricing direction",
            "enum": [
              "Input",
              "Output",
              "Cached Input"
            ],
            "type": "string"
          },
          "license": {
            "description": "License class, e.g. 'open', 'restricted', 'proprietary'",
            "type": "string"
          },
          "limit": {
            "default": 20,
            "description": "Results to return (default 20)",
            "maximum": 100,
            "minimum": 1,
            "type": "integer"
          },
          "max_price": {
            "description": "Maximum price in the SKU's own unit (per 1,000 tokens for token models)",
            "type": "number"
          },
          "min_context_window": {
            "description": "Minimum context window in tokens",
            "type": "integer"
          },
          "modality": {
            "description": "Text, Multimodal, Image, Video, Audio, Voice",
            "type": "string"
          },
          "model_family": {
            "description": "Model family, e.g. 'Llama', 'Qwen', 'Claude'",
            "type": "string"
          },
          "offset": {
            "default": 0,
            "description": "Offset for paging",
            "minimum": 0,
            "type": "integer"
          },
          "open_source": {
            "description": "'true' for models with published weights",
            "type": "string"
          },
          "origin": {
            "description": "Creator's home country, e.g. 'United States', 'China'",
            "type": "string"
          },
          "reasoning": {
            "description": "'true' for reasoning models only, 'false' to exclude them",
            "type": "string"
          },
          "tier": {
            "description": "Lineup tier: 'Flagship', 'Core' or 'Compact'",
            "type": "string"
          },
          "vendor": {
            "description": "Vendor name or id",
            "type": "string"
          }
        },
        "type": "object"
      },
      "name": "search_models"
    }
  ]
}

What the leaf hashes

{"body":"e028d2f46e1f1e0c2808c7ad6b35b705417829c7fa9336d273acd44a40ebfc3c","id":569625,"kind":"mcp.tools","method":"probe.mcp/1","observed_us":1793139427589119,"prev":null,"subject":"3c47c168-0da3-4853-8144-3a622bc590d0","subject_kind":"endpoint"}

Proof

Fold these into the leaf in order, hashing each sorted pair with keccak256, to reach the root of 2026-10-27 (273461 rows).

1. 0x6619c3da0f05f2b493cf3d24ad2391fa56ae56e3b2ad3723888e7d1ed1495f4b
2. 0x6f4759118683247516c9074866284daed4613b2f28296c6a52c66e9a6a7a14cd
3. 0x433e1b1da715cb209bd33a55d6f45c2ec866f9c0144e409e1b3fd70b32a62918
4. 0x6e45d947a47f16eacbcb91438d91871b58b1f23bbb79cd049583464123227ded
5. 0x8ba561179d9d677147440ae2b90c7ac96b2059ad2a14c52311e1845f57f38891
6. 0x9703c8f78962ba4f909eb693370860bef6383e39c90cdbc112f97d759489a4a1
7. 0x940d98778481ce41b7274a3eaa47d215025b5b1dbc516026cc0b53d92036d532
8. 0x24c55d466cce83c1e0430e5ae8411322afb4a0262d12c3f32ccd1447af0a5a78
9. 0x3233c14b531d210df838ccd0675bc3bb08c2a9ffe2b0e2a3c8762b0931892c40
10. 0xa7cbb8858264e8d035c4c8c9f44bacf605dcf936e96a132ec2b57cf640e1d117
11. 0x2790beb45139410d982bf832095cfc669288d124f5200d2bdd191f14d8df7e4e
12. 0xfc80c3ec28002b5abbe969b82c8409cc3216ef75df720eab92db371621f671d9
13. 0x4c257542b0421f909cc313308d9054fb29b4b46d9dca1b83169d04797233fda2
14. 0x3c5462812bd2f841e3d7deefc01555f18262fe5e0d5a7eb155330b7a7cb0388e
15. 0x6f00f0da417f4126951ba8ba9b7962c847e91f5c61364ad9ad47e5f979698a60
16. 0x23cf9bb4337ee8be7fcae368fd69d24c62c11fb45882127b4cd919bb96a19996
17. 0x0e01aa9525097570a6edaf32bfc959de57bf5c24317cf10c0716affea85ca60d
18. 0xa20d48798a34aba12eb9c7297722982d910f06c148f5e27ac59307422964a585
19. 0x9fc354c0ea3efc3f1b6548bb77ea902a50f2c9647647ea61592efce2bd795699

Day root

0xdd77e5e99da32c3f154180d63e3c3e6fe11e896a2c6896412ef6b5c4bcf7e795

Chained

0x23bb4dfd09f55c15ac3962f53578e02c6114d5bfd9bb451cf8794fb6e2817ef4

Published

On Arc Testnet, block 69414147: 0xb2ebd83aafeb765a0ce66e76aefb133ed06606c98038fd56191e2bcd1dcb77b4