If filled, this price will be used for a temporary "Custom" model in the results.
Per request: (fresh input × input price + cached input × cached price + output × output price) / 1,000,000
Monthly: per request cost × number of requests
Cached portion uses the model's cached input price when available (typically ~10% of input price).
Always verify on official pages:
Anthropic ·
OpenAI ·
Google ·
xAI