Get API key

Use case

GPT-5.5 coding

coding notes for gpt-5.5: 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 $1.10 on corouter (input $0.500, output $0.600).

The ID to send for code

GPT-5.5 keeps the GPT-5.6 Sol list rate on input and output, with a cache-read rate and no cache-write rate. Send gpt-5.5 when a workload was already qualified on that exact ID.

GPT-5.5 is listed with these modalities: Chat, Reasoning, Code, Vision. Coding loops often emit more output than chat, so read the output rate first: $3.00 per million tokens.

One coding-sized sample

A sample of 1 million input tokens plus 200 thousand output tokens is about $1.10 on corouter (input $0.500, output $0.600).

Questions

Which model ID should the request send?
Send gpt-5.5. 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.