--- title: AI Gateway Observability product: vercel url: /docs/ai-gateway/observability-and-spend/observability canonical_url: "https://vercel.com/docs/ai-gateway/observability-and-spend/observability" last_updated: 2026-09-08 type: reference prerequisites: - /docs/ai-gateway/observability-and-spend - /docs/ai-gateway related: - /docs/ai-gateway/observability-and-spend/logs summary: Monitor AI Gateway requests in the Vercel dashboard. Inspect token usage, latency, spend, and logs at team, project, and API key scopes. install_vercel_plugin: npx plugins add vercel/vercel-plugin search_with_vercel_cli: npx vercel@latest docs search "" --- # AI Gateway Observability The AI Gateway logs spend, model usage, and observability metrics related to your requests, which you can use to monitor and debug. ## Related pages > **For AI agents:** Follow these links to understand how this page connects to the rest of the Vercel ecosystem. For the full cross-link map (inbound, outbound, prerequisites, and semantic neighbors), see the .graph.md link below. - [Set up coding agents in one command with AI Gateway](https://vercel.com/changelog/set-up-coding-agents-in-one-command-with-ai-gateway) - [How to architect an AI evaluation dashboard on Vercel](https://vercel.com/kb/guide/ai-evaluation-dashboard-architecture-on-vercel) — Map eval orchestration, traces, and run storage to AI Gateway, Observability, and Marketplace Postgres, and learn when s - [Cost-aware model routing with Vercel AI Gateway](https://vercel.com/kb/guide/cost-aware-model-routing-with-ai-gateway) — Send easy requests to a lower-cost model and escalate only the complex ones to a frontier model through AI Gateway, with - [Build realtime voice agents on AI Gateway](https://vercel.com/blog/realtime-voice-agents-on-ai-gateway) - [AI Gateway logs now have a dedicated page](https://vercel.com/changelog/ai-gateway-logs) - [AI Gateway now supports team and project spend budgets](https://vercel.com/changelog/ai-gateway-spend-budgets-and-alerts) - [Observability](https://vercel.com/docs/observability) — Find production errors, capture request traces, and discover queryable metrics with Vercel Observability and Vercel CLI. - [Chatbox with AI Gateway](https://vercel.com/docs/ai-gateway/coding-agents/chatbox) — Connect Chatbox to AI Gateway. Configure your API key, endpoint, and models to use multiple AI providers and monitor cha - [AI Gateway Framework Integrations](https://vercel.com/docs/ai-gateway/ecosystem/framework-integrations) — Connect Flue, LangChain, LiteLLM, LlamaIndex, Mastra, Pydantic AI, TanStack AI, and other frameworks to Vercel AI Gatewa - [Flue with AI Gateway](https://vercel.com/docs/ai-gateway/ecosystem/framework-integrations/flue) — Route Flue agent requests through Vercel AI Gateway with the built-in provider, using an API key or Vercel OIDC authenti - [Flue with Vercel](https://vercel.com/docs/frameworks/agents/flue) — Create a Flue agent that uses Vercel AI Gateway for model requests, then add Vercel Sandbox for isolated code execution. Full cross-link map for this page: [/docs/ai-gateway/observability-and-spend/observability.graph.md](/docs/ai-gateway/observability-and-spend/observability.graph.md) You can view these details in the [**AI Gateway Overview**](https://vercel.com/d?to=%2F%5Bteam%5D%2F%7E%2Fai-gateway\&title=AI+Gateway) section in your Vercel dashboard sidebar: - **Usage**: Graphs and metrics to track your AI Gateway usage and cost - **Requests**: Summaries by project, API key, and a detailed log of all requests You can view these metrics in two ways: - **Team level**: Stay in your team scope to see aggregated metrics across all projects - **Project level**: Use the new dashboard view and select a specific project from the top project dropdown to see project-specific metrics ## Usage The **Usage** section displays four metrics to help you monitor your AI Gateway activity. You can look back at most 36 days. ![Image](https://7nyt0uhk7sse4zvn.public.blob.vercel-storage.com/docs-assets/static/docs/ai-gateway/overview-observability/graphs-light.png) ### Requests by model The **Requests by Model** chart shows the number of requests made to each model over time. This can help you identify which models are being used most frequently and whether there are any spikes in usage. ### Time to first token (TTFT) The **P50 TTFT** chart shows the median (P50) time it takes for the AI Gateway to return the first token of a response. This can help you understand the latency of your requests and identify any performance issues. ### Input/output token counts The **All Tokens** chart shows the number of input and output tokens for each request. This can help you understand the size of the requests being made and the responses being returned. ### Spend The **Spend** chart shows the total amount spent on AI Gateway requests over time. This can help you monitor your spending and identify any unexpected costs. ## Requests The **Requests** section displays summaries by project, API key, and a detailed log of all requests. Each summary includes request count, average tokens per second, P50 duration, P50 TTFT, and cost for the specified time frame. ### Projects View usage grouped by project. Use this view to associate usage and spend with specific projects. Click into a project for more detailed information. ![Image](https://7nyt0uhk7sse4zvn.public.blob.vercel-storage.com/docs-assets/static/docs/ai-gateway/overview-observability/projects-summary-light.png) ### API keys View usage grouped by API key. Use this view to track usage by a specific person or part of your organization. Click into an API key for more detailed information. ![Image](https://7nyt0uhk7sse4zvn.public.blob.vercel-storage.com/docs-assets/static/docs/ai-gateway/overview-observability/apikeys-summary-light.png) ### Logs The overview summarizes traffic. To work with individual requests, open the [Logs](/docs/ai-gateway/observability-and-spend/logs) page, where you can search by request ID, filter by model, provider, or status code, follow requests live, and open one request to see how it was routed. You can also export the filtered list as CSV or JSON. ## Team scope By default, when you access the **AI Gateway Overview** tab, you view metrics for all requests made across all projects in your team. This is useful for monitoring the overall usage and performance of the AI Gateway. ## Project scope To view metrics for a specific project, you can access the project scope in two ways: 1. Select the project from the top project dropdown in the dashboard 2. Click into the project from the **Projects** view in the **Requests** section Once in project scope, you'll see the same metrics filtered to show only the activity for that specific project. ## Search the docs from your terminal Search the Vercel docs and read pages as Markdown with the Vercel CLI. No login required. ```bash # Find docs pages by keyword npx vercel@latest docs search "environment variables" npx vercel@latest docs search "function timeout" # Print a docs page as Markdown, by path or URL npx vercel@latest docs inspect ``` --- [View full sitemap](/docs/sitemap) If you encounter incorrect information, can’t find what you need, need a capability Vercel doesn’t currently offer, or have any other feedback to report, please do it by following the instructions at https://vercel.com/feedback.md.