Infrastructure · llms.txt file breakdown
Vercel provides routes into Vercel documentation, including When to use Vercel, How agents should use Vercel, Agent setup, Documentation.
The actual file
The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.
Complete saved Markdown shown below.
# Vercel
> Vercel is a cloud platform for building, deploying, and scaling web applications and AI workloads.
Use this index to find machine-readable documentation and platform resources. Follow the linked indexes when you need individual pages.
## When to use Vercel
- Deploy and scale web applications, APIs, and AI workloads from a Git repository or the Vercel CLI.
- Automate projects, deployments, domains, and account resources through the Vercel REST API or SDK.
- Connect an authenticated AI assistant to Vercel projects, deployments, logs, analytics, and documentation through Vercel MCP.
- Route AI requests across providers through Vercel AI Gateway, with automatic fallbacks, spending controls, usage monitoring, and no markup on token prices.
- Run untrusted or agent-generated code in isolated Vercel Sandboxes.
## How agents should use Vercel
- For research, fetch the Markdown documentation indexes below and follow their links to individual Markdown pages.
- For REST API calls, read the OpenAPI description and authentication documentation before choosing an operation. Ask for approval before changing account resources.
- For Vercel MCP, use an OAuth-capable MCP client and let the user authorize access to their Vercel account.
## Agent setup
- [Set up Vercel for your coding agent](https://vercel.com/get-started.md): Follow the agent playbook to install the CLI, add Vercel guidance, and connect Vercel MCP.
- [Getting started with Vercel](https://vercel.com/docs/getting-started-with-vercel.md?from=llms-txt): Install the Vercel CLI, add the Vercel plugin or Vercel Skills, and deploy your first project.
- [Vercel plugin](https://vercel.com/docs/agent-resources/vercel-plugin.md?from=llms-txt): Install with `npx plugins add vercel/vercel-plugin`, or `opencode plugin add github:vercel/vercel-plugin` in OpenCode, for Vercel skills, commands, and specialist agents.
- [Vercel Skills](https://vercel.com/docs/agent-resources/skills.md?from=llms-txt): Browse and install individual skills for coding agents that do not support the plugin.
## Documentation
- [Vercel product documentation](https://vercel.com/docs/products.md): Curated product index with links to documentation.
- [Documentation sitemap](https://vercel.com/docs/sitemap.md): Documentation pages with summaries and prerequisites.
- [Full documentation content](https://vercel.com/docs/llms-full.txt): Complete documentation and REST API reference in one file.
## REST API and developer resources
- [Vercel REST API documentation](https://vercel.com/docs/rest-api.md): Endpoint reference for the public Vercel REST API.
- [Vercel REST API OpenAPI description](https://vercel.com/openapi.json): Machine-readable OpenAPI 3.0 description for the public REST API.
- [Vercel REST API authentication](https://vercel.com/docs/accounts/access-tokens.md#use-a-scoped-token-with-the-api): Create scoped access tokens and use them as Bearer tokens in API requests.
- [Vercel webhook documentation](https://vercel.com/docs/webhooks.md): Event subscriptions, payloads, and delivery behavior.
- [Vercel MCP server](https://vercel.com/docs/agent-resources/vercel-mcp.md): OAuth-authenticated tools for Vercel documentation and account resources.
## Self-serve onboarding
- [Find a domain with Vercel CLI or API](https://vercel.com/domains/get-started.md): Search available names, compare registration and renewal prices, and return a verified shortlist. Neither requires authentication.
- [Vercel Hobby plan](https://vercel.com/docs/plans/hobby.md): Free plan for non-commercial personal projects.
- [Vercel CLI tokens](https://vercel.com/docs/cli/tokens.md): Create and manage personal access tokens for the Vercel API and CLI.
- [Vercel AI Gateway](https://vercel.com/docs/ai-gateway.md): One API for AI models, with routing, fallbacks, and usage monitoring.
- [AI Gateway models](https://vercel.com/ai-gateway/models.md): Every AI Gateway model with pricing, context window, providers, and capability tags.
- [AI Gateway model list API](https://ai-gateway.vercel.sh/v1/models): Live JSON list of every model ID with pricing and capabilities. No API key required.
- [Vercel Sandbox](https://vercel.com/docs/sandbox.md): Isolated compute for running code and agent workloads.
- [Vercel Templates](https://vercel.com/templates.md): Deployable starter projects for frameworks, AI, storage, and more, each with a one-click deploy link.
## Knowledge Base
- [Knowledge Base](https://vercel.com/kb.md): Featured and recent guides, plus a directory of topics.
- [Knowledge Base sitemap](https://vercel.com/kb/sitemap.md): Troubleshooting guides, topics, videos, bulletins, and product references.
## Learning and updates
- [Vercel Academy](https://vercel.com/academy/llms.txt): Courses and learning paths.
- [Vercel Blog sitemap](https://vercel.com/blog/sitemap.md): Articles, engineering posts, and product announcements.
- [Vercel Changelog sitemap](https://vercel.com/changelog/sitemap.md): Product updates and release notes.
## Optional
- [Agent resource catalog](https://vercel.com/.well-known/ai-catalog.json): Experimental catalog of agent-facing resources.
- [Product taxonomy](https://vercel.com/docs/taxonomy.json): Canonical product names, aliases, and deprecations.
- [Documentation graph](https://vercel.com/docs/graph.json): Cross-site links, prerequisites, semantic neighbors, and related pages.
Measured from the saved file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
Vercel is a cloud platform for building, deploying, and scaling web applications and AI workloads.
Context architecture
9 H2 sections organize 28 parsed Markdown links. 21 links point to .md or .markdown paths; 1 link occurrences use another hostname. Linked destinations have not been recursively validated.
| H2 section | Links | UTF-8 bytes | Tokens |
|---|---|---|---|
| When to use VercelLine 7 | 0 | 560 | 119 |
| How agents should use VercelLine 15 | 0 | 393 | 74 |
| Agent setupLine 21 | 4 | 800 | 217 |
| DocumentationLine 28 | 3 | 371 | 77 |
| REST API and developer resourcesLine 34 | 5 | 736 | 176 |
| Self-serve onboardingLine 42 | 8 | 1165 | 280 |
| Knowledge BaseLine 53 | 2 | 241 | 58 |
| Learning and updatesLine 58 | 3 | 310 | 78 |
| OptionalLine 64 · Optional | 3 | 371 | 84 |
1 distinct links point to other llms.txt paths. These are routes to more indexes, not proof their contents were included in this file.
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
1 H2 section named “Optional” contain 3 parsed links. 25 links sit outside those sections. That puts 10.7% of the file’s parsed links under Optional.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
MCP-related text was detected in the captured file. 1 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
These are text and link observations. No MCP server connection, authentication or tool call was tested.
Index and bundle
Verified text companion
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
This capture establishes a baseline. Update frequency cannot be determined from one observation.
1 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
4ab4c962d55a7b4bc5b9b3fdfdc8aa4b82f3541242743d226f83a1bcbf53a69dCounts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.