About ModelBank & methodology

ModelBank is an independent, automatically updated ledger of AI models and services. It is not affiliated with any AI vendor.

Status monitoring

Every 2 minutes a Cloudflare Worker checks each service in two ways: (1) it reads the vendor’s official status page (when a machine-readable one exists), and (2) it sends an unauthenticated request to the vendor’s public API endpoint from Cloudflare’s edge. Any HTTP response below 500 (including 401 “missing API key”) means the API front door is reachable. Timeouts, network errors and 5xx responses are retried once and then counted as a failure. A service is marked Outage when our probe fails or the vendor declares a major/critical incident, and Degraded for minor incidents, maintenance or response times above 5 seconds. Uptime = (operational checks + ½ degraded checks) / all checks.

Limitations: the probe confirms the API is reachable, not that every model returns correct completions. Model-level errors are reflected via official incidents and per-provider uptime.

Prices & models

Model metadata and prices are synced hourly from public model catalogs (primarily the OpenRouter public models API, which lists vendor list prices). Prices are shown in USD per 1 million tokens. “Blended” price assumes 3 input tokens per output token. Every change is stored, so price history starts on the day tracking began. Benchmark indices come from Artificial Analysis via the same catalog.

Contact

Corrections, data partnerships or listing a service: [email protected]