Use case
GPT-5.3 Codex API
API notes for gpt-5.3-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
GPT-5.3 Codex is a coding ID with a 272K window. Its list rate matches GPT-5.2 Codex; the difference you bill is the ID itself, gpt-5.3-codex.
Put gpt-5.3-codex in the model field. The base URL is https://api.corouter.co. Familiar JSON shapes stay familiar. Do not treat a feature as covered until your own production traffic has checked it.
Rate card
GPT-5.3 Codex (gpt-5.3-codex) lists at $1.75 input and $14.00 output per million tokens. corouter bills $0.350 input and $2.80 output. Context is 272K.
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-5.3-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.