> For the complete documentation index, see [llms.txt](https://docs.apismart.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.apismart.ai/api-usage/usage-logs-and-costs.md). # Usage Logs and Costs Learn how to use ApiSmart Usage Logs to monitor API requests, consumption, costs, latency, success rates, and request-level details. Use **Usage Logs** in the ApiSmart Console to monitor API activity, review request-level consumption and costs, and investigate performance or request issues. Usage Logs help you understand which API Keys and models are generating usage and how individual requests affect your account balance. ### 📊 Usage Overview Sign in to the ApiSmart Console and go to: **Console → Usage Logs**
At the top of the page, you can view four summary metrics: | Metric | Description | | -------------------- | ------------------------------------------------- | | **Total Cost ($)** | Total API cost for the selected records or period | | **Total Tasks** | Number of API tasks recorded | | **Avg Latency (ms)** | Average request processing latency | | **Success Rate** | Percentage of requests completed successfully | These metrics provide a quick overview of API usage, cost, and performance. ### 🔍 Filter Usage Records Use the filters to narrow down the records you want to review. Available filters include: * **Date** — View records for a selected date * **API Key Name** — Filter requests made with a specific API Key * **Model Type** — Filter by model or workload type * **Model Name** — Filter by a specific model * **Billing Mode** — Filter by the billing method applied * **Status** — Filter by request status After selecting your filters, click **Search**. Use **Reset** to clear the current filters and return to the default view. > The Console may temporarily display **Token Name** while the product terminology is being updated. ApiSmart documentation uses **API Key** for API authentication credentials. ### 📋 Understand Usage Records Each row in Usage Logs represents a recorded API request or task. The table can include the following fields: | Field | Description | | ----------------- | ------------------------------------- | | **Request ID** | Unique identifier for the request | | **Time** | Time the request was recorded | | **API Key Name** | API Key associated with the request | | **Model** | Model used for the request | | **Type** | Request or workload type | | **Billing Mode** | Billing method applied to the request | | **Duration (ms)** | Request processing duration | | **Consumption** | Usage recorded for the request | | **Result** | Request result information | | **Cost** | Amount charged for the request | | **Status** | Request status | The exact meaning of **Consumption** depends on the model and billing mode. It should not always be interpreted as text token usage. For model-specific billing rules, see [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md). ### 💰 Review Request Costs Use the **Cost** field to review the amount charged for an individual request. The **Total Cost ($)** metric at the top of the page provides an aggregate view of API costs for the records included in the current view or selected filters. Different models may use different billing methods. For example, billing can depend on factors such as: * Token usage * Number of generated images * Video duration * Generated video tokens * Resolution * Model-specific request parameters For current billing rules, see [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md). ### ⚡ Monitor API Performance Usage Logs can also help you monitor API performance. #### Avg Latency **Avg Latency (ms)** shows the average processing latency for recorded requests. Individual request duration is available in: **Duration (ms)** Use this information when investigating slow requests or comparing API performance across models. #### Success Rate **Success Rate** shows the percentage of requests that completed successfully. If the success rate drops unexpectedly, review individual records and pay attention to: * Status * Result * Model * Request ID * Request time For API error information, see [**HTTP Status Codes and API Errors**](/troubleshooting/http-status-codes-and-api-errors.md). ### 🧩 Filter by Model and Billing Mode The **Model Type**, **Model Name**, and **Billing Mode** filters can help you separate different kinds of usage. For example, you can use them to: * Review usage for a specific model * Compare activity across model types * Investigate requests using a particular billing mode * Identify which workloads are contributing most to your API costs Because text, image, and video models can use different billing methods, filtering by model and billing mode can be particularly useful when reviewing costs. ### 🔑 Review Usage by API Key Use the **API Key Name** filter to review activity associated with a specific credential. This can help when you use separate API Keys for: * Development * Testing * Production * Different applications * Different backend services Using descriptive API Key names makes request activity easier to identify in Usage Logs. For API Key management, see [**Create and Manage API Keys**](/welcome-to-apismart/api-keys/create-and-manage-api-keys.md). ### 📤 Export Usage Records Usage Logs allows you to select records and use **Export Selected** to export the selected data. Exported records can be useful for: * Internal reporting * Cost analysis * Troubleshooting * Usage reviews * Comparing models or API Keys Apply filters first if you only need records from a specific date, model, API Key, or status. ### 🔎 Investigate a Specific Request When troubleshooting an individual request, start with its **Request ID**. Review the corresponding record for: * Request time * API Key * Model * Type * Billing Mode * Duration * Consumption * Result * Cost * Status The Request ID can also help identify the request when contacting ApiSmart Support. Never provide your full API Key to support. ### ⚠️ Unexpected Usage or Cost? If API usage or costs are higher than expected: 1. **Filter by API Key**\ Identify which credential generated the requests. 2. **Check Model and Billing Mode**\ Different models can use different pricing methods. 3. **Review Consumption and Cost**\ Compare individual requests to identify where usage increased. 4. **Check for Repeated Requests**\ Retries, duplicate calls, or automated workflows may generate additional usage. 5. **Review Request Status**\ Use Status and Result to investigate unusual request behavior. If you still cannot explain the usage, contact [**ApiSmart Support**](/help-and-resources/contact-support.md) with the relevant **Request ID**. ### 💳 Usage Logs and Your Wallet Usage Logs show outgoing API activity, while your Wallet shows your current available balance. A typical flow is: **Wallet balance → API request → Usage recorded → Cost calculated → Balance deducted** For account-level payment and recharge information, see: * [**Add Funds and Understand Wallet Credits**](/account-and-wallet/add-funds-and-understand-wallet-credits.md) * [**View Your Balance and Transaction Records**](/account-and-wallet/view-your-balance-and-transaction-records.md) ### ➡️ Next Steps Continue with: * [**Model Pricing and Billing**](/models-and-pricing/model-pricing-and-billing.md) — Understand model-specific billing methods * [**View Your Balance and Transaction Records**](/account-and-wallet/view-your-balance-and-transaction-records.md) — Review wallet and payment activity * [**Create and Manage API Keys**](/welcome-to-apismart/api-keys/create-and-manage-api-keys.md) — Manage API credentials * [**HTTP Status Codes and API Errors**](/troubleshooting/http-status-codes-and-api-errors.md) — Troubleshoot API failures