Skip to content
← Back to guides

FAQ

Will my model be swapped for a cheaper one?
No. Requests go to the model you choose, with no downgrades or swaps.
How is usage billed?
Each request is charged from your balance by actual usage: input and output tokens, each multiplied by the model’s price (USD per million tokens). See Model pricing; usage records in the console are the record of what was charged.
What is the base URL?
For the OpenAI-compatible format use https://api.6090ti.com/v1; for the Anthropic-compatible format use https://api.6090ti.com.
Do I need a separate key for each tool?
No. One key calls every model enabled for you. You can still create a key per computer or project to see usage separately and disable one on its own.
How do I see which models my key can use?
Request https://api.6090ti.com/v1/models with that key; the response lists the models available to it.
Why does one message create several charge records?
Coding tools often send several requests in the background for one message, and each request is charged separately. See FAQ: charges, balance and usage records.
What happens when my balance runs out?
Requests return 403 with error code INSUFFICIENT_BALANCE. Top up and continue; you do not need a new key.
What if my API key leaks?
Disable the leaked key in the console right away, create a new one, and check usage records for unusual calls. Changing your password does not revoke existing keys.