Token4AI CloudToken Usage, Cost Tracking & API Keys
The Token4AI console brings model access, request history, spending and support together. Use the overview to see account activity, then open individual requests or support chat for the context you need.
By the Token4AI Cloud product team
How do I track tokens and spending?
The overview displays daily spending and total token consumption. Compact k, m and b units keep large token totals readable. Use request history to examine individual requests, including the model, status and usage.
A request count and a token count measure different things. One request can consume different amounts of tokens depending on the input and generated output. Check the current billing rules and account balance when planning usage.
How should I organize API access?
Create application API keys in the console and choose the appropriate key when configuring an agent. Separate keys let you manage credentials for different applications without sharing a single secret everywhere.
Keep API keys on the server and revoke exposed credentials. When a task reports an invalid key, check its configuration before retrying.
How do I contact customer support?
- Open the customer support entry in the console.
- Describe the problem, the operation you attempted and when it occurred. Include a request ID if one is available.
- Upload relevant screenshots or files directly in the conversation. Remove passwords, API keys and unrelated personal information before sending.
- Keep the conversation together so the support team can review the text and attached evidence in context.
What about cloud agent failures?
Open the task’s event log and identify the failing step before contacting support. The event cards and duration timeline provide more useful context than the final reply alone.
A 429 status indicates a rate-limited request, but the status alone does not identify which layer imposed the limit. Include the request ID and failure details so the request path can be investigated.