Use case
GPT-6 Astra Codex
Codex notes for gpt-6-astra: 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 $4.00 on corouter (input $2.00, output $2.00).
The model ID in a Codex client
In a Codex-related client, set the model to gpt-6-astra 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-6 Astra is the highest standard list rate in the GPT rows here. Send gpt-6-astra when the task is worth that output rate and you want the 1.05M window with image input.
Coding volume
GPT-6 Astra (gpt-6-astra) lists at $10.00 input and $50.00 output per million tokens. corouter bills $2.00 input and $10.00 output. Context is 1.1M.
A sample of 1 million input tokens plus 200 thousand output tokens is about $4.00 on corouter (input $2.00, output $2.00).
Questions
- Which model ID should the request send?
- Send gpt-6-astra. 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.