Pay for what you use
Add prepaid balance in the AsterWise app. Successful requests are charged against that balance. Purchased balance does not expire. There is no subscription or seat fee. Failed and cancelled requests are not charged. Open Usage in the app to see each request and its charge.What is a token?
Tokens are small pieces of text used to measure a request. Input tokens come from the content you send, including conversation history. Output tokens come from the generated response. Token counts are not the same as word counts.
When reasoning tokens are reported, they count toward output usage. Cached input uses the standard input rate.
Rate limits
AsterWise currently has no requests-per-minute or tokens-per-minute rate limits. This does not mean a single request can be unlimited in size. The model and your tool still have context and output limits. Account balance, spending controls, and simultaneous-request controls also apply.Context and output limits
The context window is how much content a model can work with in one request. The output limit is how much it can generate in its response. A setting such asmax_tokens controls response length; it is not a rate limit.
Use the recommended settings on the app’s Setup page. If a request is too large, shorten the prompt, remove unnecessary conversation history, or split the task into smaller requests.
If a request stops unexpectedly, check Usage before trying again. See troubleshooting for help.