API

All data is published as static JSON, regenerated on every build. No key needed, and cross-origin requests are allowed.

Endpoints

API endpoints
Path	Returns
`/api.json`	Everything: metadata and the full rating of every model
`/api/models.json`	Model list: id, name, vendor, status
`/api/models/<provider>/<model>.json`	One model, in the same shape as an item of the full dump
`/api/history.json`	The ratings as recorded each day; the changelog and trend charts come from it

Example

curl https://mekiki.fog.moe/api/models/anthropic/claude-fable-5-2.json

This is the live response for anthropic/claude-fable-5-2.

{
  "id": "anthropic/claude-fable-5-2",
  "name": "Claude Fable 5.2",
  "vendor": "Anthropic",
  "status": "active",
  "intelligence": {
    "score": 100,
    "tier": "top",
    "label": "Top",
    "labels": {
      "en": "Top",
      "zh-CN": "最高",
      "zh-TW": "最高"
    },
    "breakdown": {
      "aa_intelligence": {
        "raw": 64.6,
        "normalized": 100,
        "weight": 0.2169
      },
      "arena_text": {
        "raw": null,
        "normalized": null,
        "weight": 0.2169
      },
      "arena_webdev": {
        "raw": 1835.76,
        "normalized": 100,
        "weight": 0.2169
      },
      "arena_agent": {
        "raw": null,
        "normalized": null,
        "weight": 0.2169
      },
      "livebench": {
        "raw": 87.15,
        "normalized": 100,
        "weight": 0.1325
      }
    }
  },
  "cost": {
    "tier": "very_high",
    "label": "Very high",
    "labels": {
      "en": "Very high",
      "zh-CN": "很高",
      "zh-TW": "很高"
    },
    "index": 87.1,
    "blended": 5.74,
    "input": 8,
    "output": 40,
    "cache_read": 0.2
  },
  "value": {
    "score": 30.2,
    "tier": "very_low",
    "label": "Very low",
    "labels": {
      "en": "Very low",
      "zh-CN": "很低",
      "zh-TW": "很低"
    },
    "cost_basis": "run_cost",
    "run_cost": 22191.42,
    "effective_price": 9.082246,
    "cost_index": 95.1
  },
  "url": "https://mekiki.fog.moe/m/anthropic/claude-fable-5-2"
}

Fields

Scores have one decimal place. Missing values are null; fields are never omitted.
tier is a stable English key. label is the English label, and labels holds the label in every language.
Prices are in USD per 1M tokens. cost.blended is the blended price of cache reads, input and output (weights on the Method page), and cost.index is its 0–100 cost index.
value.effective_price is the price the value score is computed from, in USD per 1M tokens, and value.cost_index is its 0–100 index. value.cost_basis says where that price comes from: run_cost when Artificial Analysis measured what the model costs to run (value.run_cost, in USD), list_price otherwise.
history.json has one entry per recorded day: its date and, for every model listed that day, the name, status, scores, tiers and prices. A day is only recorded when something changed, so each entry holds until the next one.

Versioning

Fields are only ever added. A breaking change bumps version. The current version is 1.

Attribution

Leaderboard data comes from Artificial Analysis, Arena and LiveBench; prices come from models.dev. Credit them too if you republish these numbers.