Use case
GPT-6 Luna prompt caching
prompt caching notes for gpt-6-luna: the rate card, a worked volume, and when to send this ID. A sample of 1 million input tokens plus 200 thousand output tokens is about $0.440 on corouter (input $0.200, output $0.240).
Cache-read rate
Cache read for gpt-6-luna lists at $0.200 and is $0.020 on corouter per million tokens. Uncached input is $0.200.
Only the input that actually hits cache is billed at the cache-read rate. This page does not promise your prompt will hit.
Where this ID sits
GPT-6 Luna keeps the 1.05M window and lists above GPT-6 Sol on output, without the Code tag. Send gpt-6-luna when you want that ID rather than gpt-6-sol or gpt-6.1-sol.
Questions
- Which model ID should the request send?
- Send gpt-6-luna. Do not put a different name in the model field.
- What is the minimum top-up?
- Prepaid credits, $5 minimum top-up, no subscription tier.