API reference

Credits: 1Also at: /search, /exa/search

Exa-compatible search. Pass contents (text, highlights, pruned_context) to get page Markdown, highlights and a query-pruned context per result, included in the 1 credit; without contents, results carry no page text. Accepts camelCase or snake_case.

Parameters

Example request

curl -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":3,"contents":{"text":true,"highlights":true,"pruned_context":true}}'

# 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);

Example response

{
  "requestId": "4f9d2c0e8b5a4b0f9a1e6c2d7b3f8a10",
  "results": [
    {
      "id": "0b6f3c1e-5d2a-5f4b-9c8e-7a1d2e3f4b5c",
      "url": "https://example.com/blog/vector-database-benchmarks",
      "title": "Vector database benchmarks",
      "score": 0.93,
      "publishedDate": "2026-02-11",
      "text": "# Vector database benchmarks\n\nWe measured recall and p99 latency for...",
      "highlights": ["We measured recall and p99 latency for..."],
      "highlightScores": [0.97],
      "prunedContext": "We measured recall and p99 latency for..."
    }
  ],
  "costDollars": {"total": 0.001},
  "searchTimeMs": 412,
  "contextfetch": {"cache": "miss", "timingsMs": {...}, "tokens": {...}, "sources": {...}}
}

Response headers

Errors

Credits: 1 per URL that loads (max 10)Also at: /contents

Fetch pages as Markdown, with optional query-aware highlights. Failed URLs come back in statuses and are not billed.

Parameters

Example request

curl -s https://api.contextfetch.dev/v1/contents \  -H "Authorization: Bearer YOUR_API_KEY" \  -H "Content-Type: application/json" \  -d '{"urls":["https://docs.python.org/3/library/asyncio-task.html"],"text":true,"highlights":{"query":"task groups"}}'

Example response

{
  "requestId": "a1b2c3d4e5f60718293a4b5c6d7e8f90",
  "results": [
    {
      "id": "c7e1a2b3-4d5e-5f60-8a9b-0c1d2e3f4a5b",
      "url": "https://docs.python.org/3/library/asyncio-task.html",
      "title": "Coroutines and Tasks",
      "text": "# Coroutines and Tasks\n\n...",
      "highlights": ["...the chunk most relevant to task groups..."],
      "highlightScores": [0.95],
      "prunedContext": "## Task Groups\n\n..."
    }
  ],
  "costDollars": {"total": 0.001}
}

Response headers

Errors

Credits: 1Also at: /findSimilar

Scrapes the URL, extracts its topic terms and searches outside its domain. Same response shape as /search.

Parameters

Example request

curl -s https://api.contextfetch.dev/v1/findSimilar \  -H "Authorization: Bearer YOUR_API_KEY" \  -H "Content-Type: application/json" \  -d '{"url":"https://example.com/blog/vector-database-benchmarks","numResults":5,"contents":{"text":true,"highlights":true}}'

Example response

{
  "requestId": "4f9d2c0e8b5a4b0f9a1e6c2d7b3f8a10",
  "results": [
    {
      "id": "0b6f3c1e-5d2a-5f4b-9c8e-7a1d2e3f4b5c",
      "url": "https://example.com/blog/vector-database-benchmarks",
      "title": "Vector database benchmarks",
      "score": 0.93,
      "publishedDate": "2026-02-11",
      "text": "# Vector database benchmarks\n\nWe measured recall and p99 latency for...",
      "highlights": ["We measured recall and p99 latency for..."],
      "highlightScores": [0.97],
      "prunedContext": "We measured recall and p99 latency for..."
    }
  ],
  "costDollars": {"total": 0.001},
  "searchTimeMs": 412,
  "contextfetch": {"cache": "miss", "timingsMs": {...}, "tokens": {...}, "sources": {...}}
}

Response headers

Errors

Credits: 1 (basic or advanced)

Tavily-compatible search. tavily-python and @tavily/core use the base URL https://api.contextfetch.dev/tavily.

Parameters

Example request

curl -s https://api.contextfetch.dev/tavily/search \  -H "Content-Type: application/json" \  -d '{"api_key":"YOUR_API_KEY","query":"vector database benchmarks 2026","max_results":3,"include_raw_content":true}'

# 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"])

// npm i @tavily/coreimport { tavily } from "@tavily/core"; const tvly = tavily({  apiKey: "YOUR_API_KEY",  apiBaseURL: "https://api.contextfetch.dev/tavily",}); const res = await tvly.search("vector database benchmarks 2026", { searchDepth: "basic", maxResults: 5 });for (const r of res.results) console.log(r.url, r.score);

Example response

{
  "query": "vector database benchmarks 2026",
  "results": [
    {
      "title": "Vector database benchmarks",
      "url": "https://example.com/blog/vector-database-benchmarks",
      "content": "We measured recall and p99 latency for...",
      "raw_content": "# Vector database benchmarks\n\n...",
      "score": 0.93
    }
  ],
  "response_time": 0.84
}

Response headers

Errors

Credits: 1

Any public URL as Markdown (text/markdown). Add ?q= to prune the page to the chunks relevant to a question.

Parameters

Example request

curl -si "https://api.contextfetch.dev/r/https://docs.python.org/3/library/asyncio-task.html?q=task+groups" \  -H "Authorization: Bearer YOUR_API_KEY"

Example response

HTTP/2 200
content-type: text/markdown; charset=utf-8
x-token-savings: 91.0
x-raw-tokens: 18240
x-output-tokens: 1650

## Task Groups
...

Response headers

Errors

Credits: 0

Credits left on a key, its auto-reload settings and the average credits used per day over the last 7 days. The key goes in a header only; ?key= is not accepted, so keys never reach access logs. MCP tool: contextfetch_balance.

Parameters

Example request

curl -s https://api.contextfetch.dev/v1/balance -H "Authorization: Bearer YOUR_API_KEY"

Example response

{
  "credits": 14873,
  "auto_reload": {
    "enabled": true,
    "threshold": 1000,
    "pack": "builder",
    "monthly_max_usd": 500,
    "spent_this_month_usd": 50,
    "last_error": null
  },
  "burn_rate_per_day": 412
}

Errors

Credits: 0

Turn auto-reload on or off, or change it. After a deduction leaves the balance strictly below threshold, the card saved at checkout buys pack once, as long as this UTC month's auto-reload spend plus the pack price stays within monthly_max_usd. Credits arrive when the payment succeeds. A declined payment turns auto-reload off and sets last_error. Through the API a key can turn it off, lower values or change the pack, but monthly_max_usd can never go above $500; a higher cap needs the browser success page. MCP tool: contextfetch_auto_reload.

Parameters

Example request

curl -s https://api.contextfetch.dev/v1/billing/auto-reload \  -H "Authorization: Bearer YOUR_API_KEY" \  -H "Content-Type: application/json" \  -d '{"enabled":true,"threshold":1000,"pack":"builder","monthly_max_usd":500}'

Example response

{
  "credits": 14873,
  "auto_reload": {
    "enabled": true,
    "threshold": 1000,
    "pack": "builder",
    "monthly_max_usd": 500,
    "spent_this_month_usd": 50,
    "last_error": null
  },
  "burn_rate_per_day": 412
}

Errors

Credits: 0

A link for a human, not an API call: answers 303 straight to Stripe Checkout (card, Apple Pay, Google Pay) for instant ($15, 15,000 credits), builder ($50, 60,000 credits), scale ($150, 200,000 credits). After payment the browser lands on https://contextfetch.dev/success, which shows the key and copies it to the clipboard. Optional query parameters opt in to auto-reload and save the card for it.

Parameters

Example request

# Open in a browser, or show it to your human:https://api.contextfetch.dev/buy/builderhttps://api.contextfetch.dev/buy/builder?auto_reload=1&threshold=1000&reload_pack=builder&monthly_max_usd=500

Example response

HTTP/2 303
location: https://checkout.stripe.com/c/pay/cs_live_...