Use case
GPT-5.2 Codex coding
coding notes for gpt-5.2-codex: 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 $0.910 on corouter (input $0.350, output $0.560).
The ID to send for code
GPT-5.2 Codex is the earlier coding ID at the same list rate and window as GPT-5.3 Codex. Send gpt-5.2-codex when the client already requests it.
GPT-5.2 Codex is listed with these modalities: Chat, Reasoning, Code, Vision. Coding loops often emit more output than chat, so read the output rate first: $2.80 per million tokens.
One coding-sized sample
A sample of 1 million input tokens plus 200 thousand output tokens is about $0.910 on corouter (input $0.350, output $0.560).
Questions
- Which model ID should the request send?
- Send gpt-5.2-codex. 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.