Modelmeter

Estimate the USD cost of an LLM API call for a given model and token counts. Returns input/output/total cost, plus reseller markup vs. the upstream model when applicable.

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id in provider/model form, e.g. anthropic/claude-opus-4-8. Use list_models to discover ids."
    },
    "input_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of input (prompt) tokens."
    },
    "output_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Number of output (completion) tokens."
    }
  },
  "required": [
    "model",
    "input_tokens",
    "output_tokens"
  ]
}

Unified card for one model in a single call: normalized pricing, capabilities (context window, vision, reasoning, tags), availability, reseller markup vs. upstream, and a price-history summary (launch vs. current price, percent change, last change date, all-time low/high).

{
  "type": "object",
  "properties": {
    "id": {
      "type": "string",
      "description": "Model id in provider/model form, e.g. openai/gpt-5-5."
    }
  },
  "required": [
    "id"
  ]
}

List available models with their current pricing. Optionally filter by provider.

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "description": "Provider id, e.g. anthropic, openai, google, venice, openrouter."
    },
    "include_unavailable": {
      "type": "boolean",
      "description": "Include deprecated/restricted/unavailable models. Default false."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 1000,
      "description": "Max rows to return. Default 200."
    }
  }
}

Historical pricing time-series for a model or provider. Each point is a dated snapshot of the per-Mtok rates.

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Model id to fetch history for."
    },
    "provider": {
      "type": "string",
      "description": "Provider id to fetch history for (all its models)."
    },
    "since": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); only points on/after this date."
    },
    "until": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); only points on/before this date."
    }
  }
}

The changelog of record for the model layer: deprecations, price changes, launches, and the market events around them. Filter by severity to find what demands action: 'breaking' (model going away, ID changing), 'action_required' (price/rate-limit/context changes), 'informational' (releases, funding).

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "description": "Filter to events touching this provider."
    },
    "type": {
      "type": "string",
      "description": "Event type, e.g. model_deprecation, pricing_change, model_launch."
    },
    "severity": {
      "type": "string",
      "enum": [
        "breaking",
        "action_required",
        "informational"
      ],
      "description": "Filter by what the event demands of consumers of the affected models."
    },
    "status": {
      "type": "string",
      "enum": [
        "verified",
        "unverified",
        "all",
        "corrected"
      ],
      "description": "Verification status. Default 'verified' (human-confirmed). 'all' = verified + unverified."
    },
    "since": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); events announced on/after."
    },
    "until": {
      "type": "string",
      "description": "ISO date (YYYY-MM-DD); events announced on/before."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500,
      "description": "Max events. Default 50."
    }
  }
}

Is my stack okay? Check a list of model ids against the record: scheduled retirements with days-remaining countdowns and migration targets, past retirements, and other breaking/action-required changes. Id matching tolerates dots vs dashes, dated snapshot suffixes, and bare or provider-prefixed forms. Call this at startup or in CI with the models you depend on.

{
  "type": "object",
  "properties": {
    "models": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 50,
      "description": "Model ids to check, e.g. [\"gpt-4o\", \"claude-sonnet-4-6\", \"gemini-2.5-flash\"]."
    }
  },
  "required": [
    "models"
  ]
}

Per-model retirement rows from the record: which model dies when, with runway and migration target. Default shows scheduled (upcoming) retirements sorted by shutdown date.

{
  "type": "object",
  "properties": {
    "provider": {
      "type": "string",
      "description": "Filter to one provider id."
    },
    "status": {
      "type": "string",
      "enum": [
        "scheduled",
        "retired",
        "all"
      ],
      "description": "Default scheduled."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 500,
      "description": "Max rows. Default 100."
    }
  }
}