Models & pricing

GET /api/models returns the public catalog: which models are available and their KhaBot prices.

{
  "models": [
    {
      "id": "z-ai/glm-5.2",
      "available": true,
      "priced": true,
      "input_per_mtok_usd": 3.0,
      "output_per_mtok_usd": 5.0,
      "cache_read_per_mtok_usd": 0.3,
      "cache_write_per_mtok_usd": 3.75
    }
  ]
}

How billing works

Cost is computed from KhaBot's own published per-model prices:

cost_billed = input_tokens/1e6 × input_price
            + output_tokens/1e6 × output_price
            + cache_read_tokens/1e6 × cache_read_price
            + cache_write_tokens/1e6 × cache_write_price

Cache prices fall back to the input price when unset. Prices are per million tokens (Mtok).

A model with no published price isn't available and returns 403 model_not_priced.

Live prices are shown on the homepage and your dashboard.