AI Usage and Cost Dashboard

the ai usage and cost dashboard is the best place to get a comprehensive overview of your organization’s ai activity and spend whether you are tracking costs across multiple providers or analyzing token usage by model or capability, this dashboard provides the insights you need to manage ai at scale you can access the dashboard by selecting ai in the analytics section of the left hand navigation menu what you’ll see spend by provider at the top of the page, you’ll see a breakdown of your ai spend by provider for the selected time range each provider is represented as a stacked area chart, letting you compare cost trends across platforms like openai, claude, aws bedrock, gemini, and others timeframe selector in the upper right hand corner, use the timeframe picker to update the date range by default, the dashboard shows month to date (mtd) toggle views in the upper right of the spend graph, you can toggle between cost and tokens to see either dollar spend or token usage over time last 30 days overview to the right of the spend graph, you’ll find a summary card that always shows your last 30 days of usage, regardless of the timeframe selected above this section includes cost per request over time total number of requests, with daily breakdowns token usage trends, including total input tokens total output tokens line graphs for each over the last 30 days this makes it easy to compare your selected timeframe with recent trends model level spend scrolling down, you’ll find a section showing spend by individual model this gives you visibility into which large language models (llms) and other ai models are driving your costs each model includes a bar chart of recent usage trends you can see exactly how much was spent on each model (e g , gpt 4, claude opus, mistral 7b, gemini) model capabilities at the bottom of the dashboard is a table showing how your ai spend breaks down by capability this helps you answer questions like are we using more spend on chat, image generation, or file search? which capabilities generate the most requests or token consumption? each row includes capability name (e g , chat completions, images) description of what it does event count (how many requests) token usage (if applicable) total cost why it matters the ai usage and cost dashboard gives you visibility into how ai resources are being consumed across teams and use cases accountability for spend by model and capability clarity to guide optimization, budgeting, and chargeback whether you’re trying to manage ai usage across departments or monitor the impact of new model deployments, this dashboard provides the visibility needed to stay in control