Use case
GPT-6.1 Sol long context
long context notes for gpt-6.1-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 $0.400 on corouter (input $0.200, output $0.200).
Window
GPT-6.1 Sol lists a 1.1M window. Tokens past that window are not silently cheaper. Truncate, split, or pick an ID with a larger window.
GPT-6.1 Sol (gpt-6.1-sol) lists at $2.00 input and $10.00 output per million tokens. corouter bills $0.200 input and $1.00 output. Context is 1.1M.
What a long prompt costs
A sample of 1 million input tokens plus 200 thousand output tokens is about $0.400 on corouter (input $0.200, output $0.200).
GPT-6.1 Sol matches the GPT-6 Sol list rate and is a separate model ID. Send gpt-6.1-sol when the client names that ID rather than gpt-6-sol.
Questions
- Which model ID should the request send?
- Send gpt-6.1-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.