Usage Logs
See the key, model, latency, token counts and cost of every API call, and filter them.
Click "Usage Logs" in the console's left menu, or go to https://ai.myaiexp.com/usage-logs, to see the details of every API call made by your account. Regular users only see their own logs.
Filter records
The filter bar at the top supports:
| Filter | Description |
|---|---|
| Time range | Defaults to today from 00:00 until now; you can change the start and end time |
| Model name | Filter by model ID, for example your-model-id |
| Type | All types by default; options include top-up, consumption, system, error and refund |
| Token name | Filter by API key name |
| Request ID | Find a single request by its request id |
Some filters only appear after you expand the additional filters. Click "Search" to apply and "Reset" to restore the defaults; you can also choose which columns to show.
Columns
| Column | Meaning |
|---|---|
| Time | When the request happened, plus the log type (such as consumption) |
| Token | Name of the API key used for the call |
| Model | The model ID actually called |
| Stream | Whether the request was streamed; streamed requests may also show output speed |
| Tokens | Input tokens / output tokens |
| Cost | Amount charged for the request (USD) |
| Latency | Response time |
| Details | Billing mode and unit prices (input / output price per 1M tokens); click to open the log details with the request ID, input / output token breakdown, cached tokens, unit prices and total cost |
Trace a single call
When you hit an error, put the request id from the error message into the "Request ID" filter to find the matching log entry, then check the model and key to work out the cause. Including this request id when contacting support is the fastest way to get help; see Troubleshooting.
FAQ
Playground
Chat with models directly in the console and try models from the model square without writing code.
Wallet
Check balance and usage, top up or redeem a code, convert quota to USD, understand billing, and what to do when your balance runs out.
This service is provided for learning and research purposes only. Please follow each model provider's usage policies.