Use case
GPT-6 Sol prompt caching
prompt caching notes for gpt-6-sol: 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 $0.800 on corouter (input $0.400, output $0.400).
Cache-read rate
Cache read for gpt-6-sol lists at $0.200 and is $0.040 on corouter per million tokens. Uncached input is $0.400.
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 Sol keeps the 1.05M window and lists well below Astra on both input and output. Send gpt-6-sol for the same request shape at the lower GPT-6 rate.
Questions
- Which model ID should the request send?
- Send gpt-6-sol. 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.