Use case
GPT-5.6 Sol Codex
Codex notes for gpt-5.6-sol: 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 $2.20 on corouter (input $1.00, output $1.20).
The model ID in a Codex client
In a Codex-related client, set the model to gpt-5.6-sol and the base URL to https://api.corouter.co. If the client only accepts its own built-in ID list, follow that list. Do not rename some other ID to impersonate this one.
GPT-5.6 Sol remains the high GPT-5.6 ID, with a list rate above GPT-6 Sol and below GPT-6 Astra. Send gpt-5.6-sol when an existing client already pins that ID.
Coding volume
GPT-5.6 Sol (gpt-5.6-sol) lists at $5.00 input and $30.00 output per million tokens. corouter bills $1.00 input and $6.00 output. Context is 1.1M.
A sample of 1 million input tokens plus 200 thousand output tokens is about $2.20 on corouter (input $1.00, output $1.20).
Questions
- Which model ID should the request send?
- Send gpt-5.6-sol. 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.