TypingMind Changelog
Feature Request Bug Report Open TypingMindOpen app
All updates

Extended prompt caching for OpenAI models

  • New
  • AI Models

Added extended prompt caching for supported OpenAI models. You can now choose 12-hour prompt caching in the API.

GPT-6.1 Sol parameters with prompt caching set to Extended instead of Standard

Extended caching costs more than the standard option. If a provider does not support it, TypingMind uses the standard duration.

Subscribe to updates View as JSON

Form not loading? Open it in a new tab