For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
CommunityAPI StatusAPI PricingSign Up
DocumentationAPI ReferencesCookbookIntegrationDeveloper Tools
DocumentationAPI ReferencesCookbookIntegrationDeveloper Tools
    • MCP Server
    • Markdown & llms.txt
LogoLogo
CommunityAPI StatusAPI PricingSign Up
On this page
  • What’s available
  • Read any page as Markdown
  • How to use it
  • When to use llms.txt vs the MCP server
  • Related pages

Markdown & llms.txt

||View as Markdown|
Was this page helpful?
Previous
Built with

These docs are published in formats that large language models read cleanly. Use them to give any LLM accurate, current context about the Sarvam API — no scraping, no stale training data.

What’s available

ResourceWhat it containsBest for
llms.txtA structured index of every page with titles, links, and summariesRetrieval — let a tool pick the right pages to load
llms-full.txtThe entire documentation concatenated into one filePasting the whole corpus into a large context window
Per-page .mdThe clean Markdown source of any single pageLoading just one topic

These follow the llms.txt convention and are regenerated with every docs deploy, so they always match what’s published.

Read any page as Markdown

Append .md to any documentation URL to get the raw Markdown, with no navigation or styling:

$curl https://docs.sarvam.ai/api-reference-docs/getting-started/quickstart.md

This is the quickest way to drop a single page into an LLM prompt or a RAG index.

How to use it

1

Give an assistant the whole API

Paste the contents of llms-full.txt into a model with a large context window when you want it to reason over the complete API in one shot.

2

Index for retrieval

Fetch llms.txt, then load only the linked pages you need (each is available as .md). This keeps prompts small and relevant.

3

Pin a single topic

Add .md to one page’s URL and include just that page when the task is narrow (e.g. only text-to-speech streaming).

When to use llms.txt vs the MCP server

Both make the docs available to AI — they suit different workflows:

llms.txt / MarkdownMCP server
How it worksYou fetch files and put them in the model’s contextThe assistant searches the docs live, on demand
Best forBulk ingestion, RAG indexes, offline/one-shot context, scriptsInteractive coding sessions in Cursor / Claude Code
FreshnessA snapshot from when you fetched itAlways queries the current docs
SetupNone — just a URLOne-time client configuration

Rule of thumb: use the MCP server when an assistant should pull docs while you code; use llms.txt when you want to load documentation into a model yourself.

Related pages

  • MCP Server
  • SDKs & Libraries
  • Errors & Troubleshooting