LLM Cost Quote

Text or token counts in, cost per model out, cheapest first, from OpenRouter's public price list with a price-fetched-at timestamp. Applies time-of-day pricing. Not charged if the price list is unavailable or no model matches.

Price: $0.0034 per call, USDC on Base (x402). Also available as the MCP tool llm_cost_quote at https://grokzilla.shop/mcp.

Text (token count approximated with our cl100k counter) or input_tokens in, cost per model out, cheapest first, from OpenRouter's public /api/v1/models price list (no key). price_fetched_at says when the prices were read (cached up to 10 minutes). Time-of-day and weekday prices OpenRouter publishes are applied for the current UTC time. Dynamic-price routers are excluded.

Call

POST /api/skills/llm-cost-quote

{"input_tokens": 3000, "output_tokens": 400, "models": ["openai/gpt-4o-mini", "google/gemini-2.5-flash"]}

text (optional): string
input_tokens (optional): integer
output_tokens (optional, default 500): integer
models (optional): array
top (optional, default 10): integer
include_free (optional, default false): boolean
request_id (optional): Optional idempotency key. Echoed back; a credit-pack redemption with the same request_id and body is charged once.

Not charged

Every non-200 has charged: false and is never settled.

422 invalid_params / 400 invalid_params: body fails the schema (checked before the 402).
400 before payment: neither or both of text and input_tokens, malformed model ids.
422 no_matching_models: none of the requested models has a fixed price on OpenRouter.
503 price_list_unavailable.

Response (paid 200)

Same envelope on every data service: ok, service, version, summary, data, confidence, sources, generated_at, data_as_of, charged, warnings, next.

{
  "ok": true,
  "skill": "llm_cost_quote",
  "service": "llm_cost_quote",
  "version": "1.0.0",
  "summary": "cheapest: openai/gpt-4o-mini $0.00069 for 3000 in + 400 out tokens",
  "data": {
    "input_tokens": 3000,
    "output_tokens": 400,
    "token_source": "caller-supplied input_tokens",
    "models_considered": 2,
    "quotes": [
      {
        "model": "openai/gpt-4o-mini",
        "name": "OpenAI: GPT-4o-mini",
        "cost_usd": "0.00069",
        "input_usd_per_mtok": "0.15",
        "output_usd_per_mtok": "0.6",
        "context_length": 128000,
        "fits_context": true,
        "time_based_price": false
      },
      {
        "model": "google/gemini-2.5-flash",
        "name": "Google: Gemini 2.5 Flash",
        "cost_usd": "0.0019",
        "input_usd_per_mtok": "0.3",
        "output_usd_per_mtok": "2.5",
        "context_length": 1048576,
        "fits_context": true,
        "time_based_price": false
      }
    ],
    "missing_models": [],
    "price_fetched_at": "2026-10-17T11:12:57Z",
    "currency": "USD"
  },
  "confidence": 0.97,
  "sources": [
    {
      "name": "OpenRouter public models list",
      "url": "https://openrouter.ai/api/v1/models",
      "fetched_at": "2026-10-17T11:12:57Z"
    }
  ],
  "generated_at": "2026-10-17T11:12:57Z",
  "data_as_of": "2026-10-17T11:12:57Z",
  "charged": true,
  "warnings": [],
  "next": [
    "token_count"
  ]
}