The $1 / 1,000 neural search & Markdown API for AI agents.

No signup. Payment when it matters.

Your agent can discover, call and pay for the API on its own. It needs a human only once, to pay.

1. 01Call it with no key. 25 requests per IP per day.

   curl -si https://api.contextfetch.dev/v1/search \
     -H 'content-type: application/json' \
     -d '{"query":"python asyncio timeout",
          "contents":{"text":true,"highlights":true}}'
   
   HTTP/2 200
   x-credits-remaining: 24

2. 02Out of free calls? 402 with a payment link your agent can show.

   402 Payment Required
   {
     "error": "keyless_limit",
     "message": "Daily free tier limit (25 requests) reached. Reload 15,000 searches for $15.",
     "checkout_url": "https://contextfetch.dev/#buy",
     "pricing": {
       "pack_size": 15000,
       "price_usd": 15,
       "unit_cost_usd": 0.001
     },
     "packs": [
       {
         "id": "instant",
         "name": "Instant",
         "credits": 15000,
         "price_usd": 15,
         "cost_per_1k": 1,
         "recommended": false,
         "checkout_url": "https://api.contextfetch.dev/buy/instant"
       },
       {
         "id": "builder",
         "name": "Builder",
         "credits": 60000,
         "price_usd": 50,
         "cost_per_1k": 0.83,
         "recommended": true,
         "checkout_url": "https://api.contextfetch.dev/buy/builder"
       },
       {
         "id": "scale",
         "name": "Scale",
         "credits": 200000,
         "price_usd": 150,
         "cost_per_1k": 0.75,
         "recommended": false,
         "checkout_url": "https://api.contextfetch.dev/buy/scale"
       }
     ],
     "action": {
       "type": "payment_link",
       "url": "https://api.contextfetch.dev/buy/instant",
       "prompt_to_user": "ContextFetch credits ran out. Reload 15,000 searches for $15: https://api.contextfetch.dev/buy/instant"
     }
   }

3. 03Your human pays once. Retry with the key.

   # action.url -> https://api.contextfetch.dev/buy/instant
   # one click to Stripe; the key is copied for you
   
   curl -s https://api.contextfetch.dev/v1/search \
     -H 'Authorization: Bearer YOUR_API_KEY' \
     -H 'content-type: application/json' \
     -d '{"query":"python asyncio timeout",
          "contents":{"text":true,"highlights":true}}'

Discovery files for agents: llms.txt, llms-full.txt, mcp.json and robots.txt.

Four ways in

• Search

  Exa-shaped search. Ask for contents and each result carries page Markdown, highlights and a query-pruned context, all in the 1 credit.

  POST/v1/search

  Credits: 1Docs → for Search

• Contents

  Any public URLs as Markdown, up to 10 per call, with highlights for a query. Failed URLs are not billed.

  POST/v1/contents

  Credits: 1 per URL that loads (max 10)Docs → for Contents

• Reader

  One URL in, Markdown out. Add ?q= to prune it; token counts come back in response headers.

  GET/r/{url}?q=

  Credits: 1Docs → for Reader

• MCP server

  Keyless stdio server for Claude Code, Cursor and other clients: contextfetch_search, contextfetch_extract_url, contextfetch_find_similar, contextfetch_deep_research, contextfetch_balance, contextfetch_auto_reload.

  npx@contextfetch/mcp

  Credits: 1 per searchDocs → for MCP server

Change the base URL, keep your code

The official Exa and Tavily SDKs work against ContextFetch. The highlighted line is the only change; use keyless as the key to try it free.

# Exa-shaped search with Markdown and pruned contextcurl -s https://api.contextfetch.dev/v1/search \  -H "Authorization: Bearer YOUR_API_KEY" \  -H "Content-Type: application/json" \  -d '{"query":"vector database benchmarks 2026","numResults":5,"contents":{"text":true,"pruned_context":true}}' # Any URL as Markdown, pruned to a questioncurl -si "https://api.contextfetch.dev/r/https://docs.python.org/3/library/asyncio-task.html?q=task+groups"

# pip install exa-pyfrom exa_py import Exa exa = Exa(api_key="YOUR_API_KEY", base_url="https://api.contextfetch.dev") res = exa.search(    "vector database benchmarks 2026",    num_results=5,    contents={"text": True, "highlights": True},)for r in res.results:    print(r.url, r.highlights)

// npm i exa-jsimport Exa from "exa-js"; const exa = new Exa("YOUR_API_KEY", "https://api.contextfetch.dev"); const res = await exa.search("vector database benchmarks 2026", {  numResults: 5,  contents: { text: true, highlights: true },});for (const r of res.results) console.log(r.url, r.highlights);

# pip install tavily-pythonfrom tavily import TavilyClient tavily = TavilyClient(    api_key="YOUR_API_KEY",  # or "keyless" for the free tier    api_base_url="https://api.contextfetch.dev/tavily",) res = tavily.search("vector database benchmarks 2026", max_results=5, include_raw_content=True)for r in res["results"]:    print(r["url"], r["score"])

# Claude Code: keyless, zero signupclaude mcp add contextfetch -- npx -y @contextfetch/mcp # Optional paid keyclaude mcp add contextfetch -e CONTEXTFETCH_API_KEY=YOUR_API_KEY -- npx -y @contextfetch/mcp # Claude Desktop / Cursor (mcpServers JSON){ "contextfetch": { "command": "npx", "args": ["-y", "@contextfetch/mcp"] } }

Measured, with the method

Numbers from the benchmark files in this repo, measured on one machine. Competitor latency and quality: not measured. We publish only what we ran.

All numbers, method and raw JSON →

Questions