Skip to main content
The Overview tab is the landing page of the Metrics Dashboard. It gives you a single-screen summary of gateway activity across both LLM and MCP traffic, helping you quickly assess health before diving into detailed tabs.
Overview tab of the metrics dashboard showing total cost, LLM calls, MCP calls, error breakdowns, guardrails summary, and top usage leaderboards

​
Top-Level Counters

Three headline metrics are displayed at the top of the page:
  • Total Cost — aggregate spend across all models in the selected time range, with a comparison to the previous period.
  • Total LLM Calls — count of all LLM API requests, with period-over-period change.
  • Total MCP Calls — count of all MCP requests, with period-over-period change.
These counters give you an instant pulse check. If cost spikes or call volume drops unexpectedly, you know to investigate further.

​
Incoming Requests

This section breaks down the total request volume by API endpoint type. Each row shows the endpoint pattern, a friendly label, and its share of total traffic:
EndpointDescription
/mcp-serverMCP Gateway
/chat/completionsChat Completion
/agent/responsesAgent Response
/messagesAnthropic Messages
/proxyProxy
/responsesOpenAI Responses
/embeddingsEmbedding
/completionsCompletion
/v2/rerankRerank
Use this to understand which API patterns dominate your traffic and how the mix is changing over time.

​
Error Breakdowns

​
Error Breakdown (Model)

Displays errors from LLM providers, with two views:
  • By Error Type — groups errors by HTTP status code (e.g. HTTP 404, HTTP 400, HTTP 429). This tells you whether errors are client-side (4xx) or provider-side (5xx).
  • By Virtual Account — shows which virtual accounts are experiencing the most errors.
Click on any row to drill down into the specific error details.

​
Error Breakdown (MCP)

Same structure as the model error breakdown, but for MCP traffic. This helps you quickly identify if a specific MCP server or integration is experiencing reliability issues.

​
Guardrails Summary

Shows the total number of guardrail evaluations and a ranked list of which guardrail groups are triggering most often. Each row shows the guardrail group name and the number of evaluations, with a breakdown of outcomes (blocked, flagged, mutated). This gives you a quick sense of whether your content policies are having the intended impact without needing to visit the full Guardrail Metrics tab.

​
Top Usage Rankings

The bottom section of the Overview tab shows ranked leaderboards to help you quickly identify the biggest consumers and most active components:
LeaderboardWhat it shows
Top ModelsMost-used models by request count
Top Model ProvidersMost-used providers (e.g. Google Vertex, OpenAI, AWS Bedrock)
Top Users by ModelUsers making the most LLM requests
Top Virtual Accounts by ModelVirtual accounts with the most LLM traffic
Top Users by MCPUsers making the most MCP requests
Top Virtual Accounts by MCPVirtual accounts with the most MCP traffic
Top MCP ServersMCP servers receiving the most requests
Top ToolsIndividual MCP tools called most frequently
Each row shows the name and the request count (current period / total). Use these to:
  • Identify which models and providers are carrying the most load.
  • Spot unexpected usage patterns — a user or virtual account consuming far more than expected may indicate a misconfiguration or runaway process.
  • Understand MCP adoption — see which servers and tools are being actively used.