- Download and set up Cursor.
- Once in the Cursor IDE, navigate to Settings → Models → API Keys
- In “OpenAI API Keys”: paste in your Pioneer API Key
- In “Override OpenAI API Base URL”: paste in
https://api.pioneer.ai/v1
Prompt caching on Claude models is opt-in. Pioneer never adds cache markers for you, and Cursor sends requests in the OpenAI format with its own prompt layout, so Claude prompt caching may not apply unless the client emits
cache_control markers. OpenAI/GPT models cache automatically. See Prompt Caching.