API for agents to scrape, search, monitor, and collect data from the web.
1,000 free credits. No card required.
Connect Context.dev
From scrappy startups to Fortune 500s, teams ship brand-powered features in days instead of quarters.
See all customers
How Mintlify used Context.dev to power a tool that transforms any GitHub repo URL into a complete, branded documentation site, and got there in under 10 minutes of integration time.
Read their story“Onboarding couldn't be simpler. Self-serve sign-up gives you an API key immediately, the documentation is thorough, and we were integrating within 10 minutes.”
Zero uses Context.dev for web scraping, live agent search, and brand data across its AI CRM. Its platform keeps data on 20M+ companies fresh, and switching providers took probably less than five minutes with Codex.
Read their story“Migrating to Context.dev was extremely easy. The APIs are clean and easy for agents to understand and implement. The Dashboard is also handy for testing out how various scraping types behave. Switching to Context.dev from our existing scraping and web search providers took probably less than 5min with Codex.”
Mastra built an onboarding MVP in an hour with Context.dev, pre-filling names and company details and tailoring the experience to each user's goals.
Read their storyTinfoil added Context.dev scraping and metadata to its web search agent in under five minutes.
Read their storySquad integrated Context.dev in five minutes to give its AI agents webpage scraping, screenshots, and structured data extraction, building on Bhanu's experience using the API at SiteGPT.
Read their storyInstant uses Context.dev to give its AI Shopify builder brand kits, URL-based inspiration, and reliable page context. The integration was running within an hour and ready for production in under a day.
Read their storyRaz uses Context.dev to give Similarweb AI agents the datapoints they need, combining scrape and brand APIs instead of building the web context layer in house.
Read their storyIdo Shamun, Co-founder of daily.dev, shares how Context.dev powers their internal enrichment system to verify companies with zero maintenance overhead.
Read their story“Happy to be a paid customer of @getcontextdev. It's great, gives us the best results with ms response times. We have tested a couple of products, and Context wins without a doubt.”
“My agent understood it perfectly. Setup was very easy. I was looking for a nice datapoint for my agents, and Context.dev was the best one in the marketplace.”
“Now that context.dev has been integrated into Ferndesk, we've been able to ship this really beautiful onboarding that integrates the customer's company throughout the entire flow.”
“We're seeing much higher activation rates for our free trials and sign-ups because of it. It's made it a lot simpler for customers to get started with DocsBot and to get to that 'aha' value moment very quickly.”
“We use Context.dev for our internal enrichment system to verify companies. The integration was straightforward. We set it up once and never had to touch it again. It just works.”
“The API integration was seamless and expedient. My team was able to get it set up and testing with production workloads within an hour of hearing what Context.dev was!”
“Just used Context.dev to help Codex build an on-brand sales deck generator for us. Came out really well!”
“It was great. Took 5 mins to integrate. We use Context.dev to give AI agents ability to scrape webpages, take screenshots, and also extract specific content from webpages.”
SimilarwebKlarnaFerndeskDaily.dev
Everything you need in one API: search, scraping, people data, and company data.
Search the web or the news and get ranked results with clean page content, not just links.
Turn any page or PDF into Markdown, HTML, structured fields, images, or screenshots in one request.
Ask a research question and get a structured answer in your JSON shape, with the sources behind it.
Watch pages on a schedule and get notified when pricing, content, or pages change.
Get Markdown, HTML, screenshots, images, or structured fields from any URL.
Discover page URLs across a domain, with titles and descriptions when available.
Scrape thousands of URLs or crawl a site in the background with one batch job.
Ask a research question and get structured answers with source URLs.
Watch pages for changes on a schedule and send updates to your webhook.
Get the company profile and the website’s design system from one domain.
Rendering, proxies, and retries run on every request. You send a URL and get the page, not a list of settings to tune.
JS executed
403
automatic
200
Every request loads in a real browser. There is no opt-out, because half-rendered HTML from a single-page app is a failure that looks like a success.
When a site blocks a request, it moves to a stronger proxy on its own. You never pick a proxy tier or pay extra for one.
Failed attempts retry with a different strategy before anything comes back to you. Retries run on our side, not in your code.
1. 0.0sRendered in a real browserJS executed 2. 1.1sBlocked by bot protection403 3. 1.2sEscalated to a stronger proxyautomatic 4. 2.0sRetried with a new strategy200
Scrape any page, map and crawl entire websites, run batches of thousands of URLs, get sourced answers, and monitor changes through one API.
import ContextDev from 'context.dev';
const client = new ContextDev({ apiKey: 'YOUR_API_KEY' });
const page = await client.web.scrape({
url: 'https://linear.app',
formats: {
markdown: true,
html: true,
screenshot: true,
},
sharedParams: { mainContentOnly: true },
});
if (page.markdown.success) console.log(page.markdown.data);
if (page.screenshot.success) console.log(page.screenshot.data);from context.dev import ContextDev
client = ContextDev(api_key="YOUR_API_KEY")
response = client.web.scrape(
url="https://linear.app",
formats={
"html": True,
"markdown": True,
"screenshot": True
},
shared_params={
"main_content_only": True
},
)
print(response)require "cgi/core"
require "context_dev"
client = ContextDev::Client.new(api_key: "YOUR_API_KEY")
response = client.web.scrape(
url: "https://linear.app",
formats: {
html: true,
markdown: true,
screenshot: true
},
shared_params: {
main_content_only: true
}
)
puts response<?php
require_once 'vendor/autoload.php';
use ContextDev\Client;
$client = new Client(apiKey: 'YOUR_API_KEY');
$response = $client->web->scrape(
url: 'https://linear.app',
formats: [
'html' => true,
'markdown' => true,
'screenshot' => true
],
sharedParams: [
'mainContentOnly' => true
]
);
var_dump($response);package main
import (
"context"
"fmt"
contextdev "github.com/context-dot-dev/context-go-sdk/v2"
"github.com/context-dot-dev/context-go-sdk/v2/option"
)
func main() {
client := contextdev.NewClient(
option.WithAPIKey("YOUR_API_KEY"),
)
response, err := client.Web.Scrape(context.TODO(), contextdev.WebScrapeParams{
URL: "https://linear.app",
Formats: contextdev.WebScrapeParamsFormats{
HTML: contextdev.Bool(true),
Markdown: contextdev.Bool(true),
Screenshot: contextdev.Bool(true),
},
SharedParams: contextdev.WebScrapeParamsSharedParams{
MainContentOnly: contextdev.Bool(true),
},
})
if err != nil {
panic(err)
}
fmt.Printf("%+v\n", response)
}curl --request POST 'https://api.context.dev/v1/web/scrape' \
--header 'Authorization: Bearer YOUR_API_KEY' \
--header 'Content-Type: application/json' \
--data '{
"url": "https://linear.app",
"formats": {
"html": true,
"markdown": true,
"screenshot": true
},
"sharedParams": {
"mainContentOnly": true
}
}'npm install context.devSignup for an account & get API key with context.dev/auth.md, then follow docs.context.dev/agent-quickstart to integrate into the codebase# Claude Codeclaude mcp add --transport http --scope user context https://mcp.context.dev/mcp# Any other MCP client: add https://mcp.context.dev/mcp# Install: docs.context.dev/install-cliexport CONTEXT_DEV_API_KEY=your_api_keycontext-dev web web-scrape-md --url https://example.comToken-efficient web extraction for agents. Context Highlights returns the relevant passages from a webpage for your query.
Why we ported Cheerio to Rust, how LLMs made it worth doing, and what changed in our HTML processing benchmarks.
Give Answers a research task and get structured JSON with source URLs. Web research for your app or agent, in one API call.
Our logo candidate list kept shrinking at random. We traced it to the file-type npm package, which shares internal state across detections and returns mismatched MIME types when called in parallel.
Learn how we discovered and fixed a ReDoS (Regular Expression Denial of Service) vulnerability that was causing our HTML parsing to timeout.
Learn how to prevent memory issues when using Sharp in Node.js. Practical tips and techniques for handling image processing at scale.
Connect web content to the places your product needs it: research, onboarding, enrichment, and retrieval.
Turn webpages and PDFs into Markdown, HTML, structured fields, images, and screenshots in one request.
Collect pages with Scrape and Crawl, add documents with Parse, and keep your retrieval index current with Monitors.
Resolve a domain to a typed brand profile, then research the company in your JSON shape, with sources.
Scrape thousands of URLs or crawl entire sites in one job, then collect results when it completes.
Connect company references and person identifiers to brand profiles and people data.
Pre-fill company fields from a work email domain so more users finish signing up.
Review our compliance status and request access to security information through the trust center.
View complianceReview the policies covering data handling, access control, and incident response.
Review policiesKeep inputs and outputs out of our logs, caches, and storage. We only record that a request was made.
How ZDR worksEverything you need to know about integrating and scaling with Context.dev.
Book demoYes. Crawl discovers and scrapes up to 500 pages into Markdown in one call, with controls for depth, page count, URL patterns, and subdomains. For larger sites, run Batches in crawl mode and collect results through pagination or a completion webhook. Use Map when you only need the URLs.
Core API limits cap concurrent requests per organization: Free allows 2; Developer 10, Pro 100, Growth 250, and Scale 500. Plans have no per-minute cap by default. Existing accounts keep their current allowances until they change plans; custom overrides can apply to either limit or both. The dashboard shows your effective limits. Batches, Monitors, webhook deliveries, logs, and feedback have separate organization limits. Enterprise can have custom limits; Logo Link has a separate quota.
Scrape waits up to 90 seconds by default. For slow or heavily protected pages, raise timeoutOpts.milliseconds (up to 300,000), set timeoutOpts.behavior to return-partial to keep the outputs that finished, and give your HTTP client a longer timeout than the request. Use Batches for large URL lists, and Prefetch to warm uncached domains before a Brand request.
We provide official SDKs for TypeScript, Python, Ruby, Go, and PHP.
AI agents can register and obtain API credentials programmatically using our agent authentication guide (auth.md). You will still need to sign in or verify your email. Share the link with your agent:
Brand Retrieve may reuse cached data up to its documented maxAgeMs, which defaults to about 90 days and is clamped to 0 through one year. A value of 0 requests a fresh Brand retrieval. For a specific correction or rebrand, use https://www.context.dev/update and treat returned media URLs as external resources that your application should handle defensively.
Yes, subdomains are fully supported.
We are constantly adding new data points to the API and have more data under the hood that we don't surface yet. If you need a specific data point, please contact us at hello@context.dev and we will be happy to surface it.
Yes. The free tier includes 1,000 API credits per month, enough for 1,000 standard scrapes, plus 10K one-time Logo Link requests, with no credit card required.
Context.dev offers Developer ($19/mo), Pro ($99/mo), Growth ($299/mo), and Scale ($499/mo), plus Enterprise for teams that need more than 2M credits a month, volume discounts, or security and procurement support. We currently do not support one-time lookups, however you can contact us to discuss options for one-time projects at hello@context.dev.
Start with Free for testing or Developer for your first workflow. Pro suits steady production usage; Growth adds capacity between Pro and Scale. Scale supports high-volume traffic and self-serve SSO / SAML. Choose Enterprise for custom volume, limits, procurement, or support. Upgrades apply immediately; downgrades apply at renewal.
Yes. Annual billing saves two months compared with monthly billing on every paid plan.
Eligible startups and nonprofits can apply for 30% off an annual paid plan for 12 months, plus private Slack Connect with our team. Existing customer deals stay unchanged. Apply at https://www.context.dev/startups.
Talk to sales if you need high-volume pricing beyond 2M credits/month, custom rate limits, annual invoicing, or help with a security or procurement review. Review our published compliance status, policies, controls, and subprocessors at https://trust.context.dev/. Reach us at hello@context.dev or through the contact page.
Scrape starts at 1 credit, or 2 with browser actions. Structured JSON extraction against your schema adds 4 when it succeeds, so 5 credits per page. Highlights and Product add 1, and PDF OCR adds 1 per recovered page. Brand and Styleguide cost 10 credits. Answers costs 10 in Fast mode or 100 in Ultra. Web and news search cost 1 credit per 10 results; People costs 20 per match. Logo Link has a separate quota.
JS rendering, anti-bot bypass, and proxies are included in the base scrape price. Browser actions raise the base to 2 credits. Successful JSON extraction adds 4 credits. Highlights and Product add 1, and PDF OCR adds 1 per recovered page.
Most failed requests are not billed. Not-found responses (404) are billed at the request’s base price. Scrape can return a 200 with failed outputs: it charges when at least one output succeeds or the target page is missing. Check key_metadata.credits_consumed for the amount charged.
The Free plan includes 1,000 API credits that renew every month. Paid plans can use Auto-Topup in 1K-credit blocks: Developer $2.20, Pro $1.80, Growth $1.40, and Scale $1.00 for new subscriptions. Existing subscriptions keep their rates. With insufficient credits and no available top-up, any plan returns 401 USAGE_EXCEEDED. Logo Link has a separate quota.
They are separate products with separate quotas. API credits meter the documented API endpoints. Logo Link returns a square logo through a direct image URL and does not consume API credits. Core API requests use the plan concurrency limit; Logo Link image delivery follows its separately documented quota and delivery policy.
Questions about the API, custom plans, or partnerships? Send us a message and the team will write back.
Click the address to copy it
For sales, support, security disclosures, and general questions.
hi@context.devWithin one business day, often the same hour.
Scrape, search, and research the web with one API. Bring the results straight into your product.
Every month. No credit card required.
