Use case
GPT-5.4 Mini tool calling
tool calling notes for gpt-5.4-mini: 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 $0.330 on corouter (input $0.150, output $0.180).
Tool definitions count as input
Tool JSON schemas count toward input tokens. Input for gpt-5.4-mini is $0.150. More tools and longer schemas raise the input bill. The output rate does not change.
GPT-5.4 Mini cuts the list rate and the window to 400K, and it has no vision tag. Send gpt-5.4-mini for shorter reasoning jobs.
Set it next to a lower output rate
GPT-5.4 Mini (gpt-5.4-mini) lists at $0.750 input and $4.50 output per million tokens. corouter bills $0.150 input and $0.900 output. Context is 400K.
A sample of 1 million input tokens plus 200 thousand output tokens is about $0.330 on corouter (input $0.150, output $0.180).
Questions
- Which model ID should the request send?
- Send gpt-5.4-mini. 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.