Use case
Codex Auto Review streaming
streaming notes for codex-auto-review: 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).
How streaming is billed
A streamed response is still billed on input and output tokens, not on how long the socket stays open. Output for codex-auto-review is $3.00 per million tokens.
A sample of 1 million input tokens plus 200 thousand output tokens is about $1.10 on corouter (input $0.500, output $0.600).
A field you can set
A familiar chat-completions shape often sets "stream": true next to "model": "codex-auto-review". On a messages shape, follow the stream field your client actually sends.
Codex Auto Review lists at the same input and output rate as GPT-5.6 Sol and is a review ID, not an alias of GPT-6 Sol. Send codex-auto-review when the caller asks for that ID.
Questions
- Which model ID should the request send?
- Send codex-auto-review. 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.

