Mintlify
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
Backed by
Combinator
CombinatorThe web {context} API for agents
One API for agents to scrape, search, monitor, and collect data from the web.
Powering products and agents at
Web data your
product can use.
Scrape clean Markdown, HTML, and screenshots from any page, then crawl whole sites and get sourced answers.
Explore the APIs
# Web scraping API for AI agents Scrape, crawl, and search the webfor AI products. ## Products- Scrape, map, and crawl- Batches, monitors, and answersScrape anything
Clean content from any URL.
Crawl websites
Every page of a site as Markdown.
Run batches
Scrape thousands of URLs.
Create monitors
Watch pages for changes.
Agentic Setup
Set it up your way.
Do it yourself in the dashboard, or let your AI agent handle the whole thing.
Do it yourself
- 1. Sign up and verify your email.
- 2. Copy your API key from the dashboard.
- 3. Install the SDK and start calling the API.
Let your agent do it
RecommendedPaste one line into your coding agent. It connects Context.dev to the agent or builds it into your app, and handles signup and your API key.
agent setup
Use curl to read https://docs.context.dev/agent-quickstart.md, then follow it to set up Context.dev for me.
For AI Native Products
The {APIs} powering your next feature
Scrape any page, map and crawl entire websites, run batches of thousands of URLs, get sourced answers, and monitor changes through one API.
Scrape anything
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 },
});
console.log(page.markdown.data);
console.log(page.screenshot.data);Every page,
fully loaded.
Rendering, proxies, and retries run on every request. You send a URL and get the page, not a list of settings to tune.
99.96%scrape success rate, no configuration
shop.example.com/products
200 OK- 0.0sRendered in a real browserJS executed
- 1.1sBlocked by bot protection403
- 1.2sEscalated to a stronger proxyautomatic
- 2.0sRetried with a new strategy200
Markdown returned2.4s · 1 credit
JavaScript rendering, always
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.
Proxies that escalate
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.
Retries that adapt
Failed attempts retry with a different strategy before anything comes back to you. Retries run on our side, not in your code.
From web scraping to
answers and automation.
Scrape, crawl, research, and keep up with the web. Build these workflows with one API.
Scrape Anything
Turn webpages and PDFs into Markdown, HTML, structured fields, images, and screenshots. Get the formats your product needs in one request.
context.devWebpages & PDFs
# Web data API for AI agents
Web scraping, data, and
search infrastructure
for AI products.Screenshot
Images
Multiple formats, one requestExample outputs
Crawl sites and run batches
Scrape thousands of URLs in one job. Process large URL lists or crawl entire sites, then collect results when the batch completes.
Example batch · MarkdownRunning
25,000 URLs
78.7%19,680 complete5,320 remaining
Paginated resultsOne dataset
Large URL lists · Full-site crawls
Ground RAG in fresh content
Collect pages with Scrape and Crawl, add documents with Parse, and use Monitors to refresh changed sources in your retrieval index.
acme.com/docs/api/auth
acme.com/blog/release-v3
acme.com/pricing
acme.com/changelog
acme.com/docs/sdk
markdown → your embeddings
Knowledge Base5 docs indexed
Monitor the web
Watch pages for changes on a schedule. Track pricing, content, and new pages, then send updates straight to your application.
example.com/pricing
Team plan
Monthly billingUnlimited projectsShared workspacesPriority support
Pricing changedWebhook sent
Checks every 6 hoursExample monitor
Get answers from the web
Ask a research question and get a structured answer with source URLs. Give your agent findings it can use and evidence it can follow.
What are Linear's main product features?
Structured answerExample response
{
"features": [
"Issues", "Projects", "Roadmaps"
]
}Sources
linear.applinear.app/featuresEnrich any entity your agent sees
Connect company references and person identifiers to useful context. Retrieve brand profiles, enrich people, and bring both into your agent’s workflow.
Y Combinator
ycombinator.comStartup accelerator helping founders build and grow their companies.
IndustryStartup accelerator
SloganFunding the future
Founded2005
LocationSan Francisco, CA
xlinkedinyoutube
Integrate in seconds
Get web data into your product in just three steps
01
Choose the pages your product needs
Scrape a single URL, map a domain, or crawl an entire site, all under one key.
02
Connect it to your workflow
Integrate in minutes with developer-friendly SDKs, clear docs, and example code.
03
Ship the feature
Power AI agents, RAG pipelines, research, and automation with live web data.
One platform · three surfaces
Scrape any URL. Crawl any site.
Extract any data point.
Scrape any page to clean Markdown, crawl whole sites, and extract structured JSON, with rendering, anti-bot bypass, and proxies included in the same REST API.
Web Extraction
Scrape anything. Choose your formats.
Get Markdown, HTML, images, screenshots, bytes, and structured fields from one Scrape call. Add Map, Crawl, and Answers as your workflow grows.
https://example.com/pricing
Request
POST /v1/web/scrape
{
url: 'https://example.com/pricing',
formats: { markdown: true }
}Illustrative MarkdownJSON
# Example pricing
Plans for your next project.
## Starter $19/mo
For your first production project.
## Team $49/mo
Shared access for your whole team.
- Annual billing available
Crawl & Map
One domain in. Every page out.
Map a site's URLs, then crawl up to 500 pages into Markdown in one call, or thousands more through Batches. Control depth, page count, and URL patterns.
example.com6 pages
- /.md
- /docs.md
- /docs/quickstart.md
- /docs/api/auth.md
- /blog.md
- /pricing.md
Included
1 credit per page. No proxy bill.
Rendering, anti-bot bypass, and proxies are part of the base scrape price. Most failed requests are not billed, so you pay for pages you can use.
JavaScript renderingAnti-bot bypassPremium proxiesMain-content filteringMarkdown, HTML, and screenshots in one callBlocked requests not billed
20K+ Developers
What developers say
Feedback from the engineers shipping with us every day.
John Acosta
“As soon as you type in the email, we use Context.dev to collect information about your brand and different logos. Context.dev saves us a lot of time right now.”
Founder @ UsePropane.ai
Nick Khami
“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.”
Engineering Manager @ Mintlify
Luke Ramsden
“Getting started is very simple. API docs are great and sign-up is self serve, with an API key generated immediately. Took 10 minutes to start integrating.”
CPTO @ Architect (tryarchitect.com)
Aaron Edwards
“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.”
Founder @ DocsBot
Sreejan
“Context.dev preserved full page content and JSON-LD on sites where Firecrawl struggled, provided useful metadata that let us remove much of our custom HTML parsing, and automatically refunded failed batch pages.”
Co-founder @ Zaraftis
CUSTOMERS
See how our customers do it
From scrappy startups to Fortune 500s, teams ship brand-powered features in days instead of quarters. See all customers
The Blog
Engineering deep dives, product updates, and practical guides for building with brand data.
FAQs
Frequently asked questions
Everything you need to know about integrating and scaling with context.dev.
Is there a free tier?
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.
Are there extra fees for JS rendering, anti-bot bypass, or premium proxies?
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.
Am I billed for failed requests?
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.
Which plan should I choose?
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.
Do you offer discounts for startups or nonprofits?
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.
What are the rate limits, and how can I increase them?
Core API limits cap concurrent requests per organization: Free allows 1; Developer 10, Pro 100, Growth 250, and Scale 500. Accounts created before concurrency limits keep their per-minute limits, and the dashboard shows which applies. Batches, Monitors, webhook deliveries, logs, and feedback have separate organization limits. Enterprise can have custom limits; Logo Link has a separate quota.
What SDKs are available?
We provide official SDKs for TypeScript, Python, Ruby, Go, and PHP.
When should I talk to sales?
Talk to sales if you need high-volume pricing beyond 2M credits/month, custom rate limits, SSO / SAML, SCIM provisioning, an uptime SLA, annual invoicing, an MSA / DPA, or a dedicated support channel. Reach us at hello@context.dev or through the contact page.
How fresh is the brand data? How often is it updated?
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.
What if I need additional data points?
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.
How do API credits work?
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.
Can I crawl an entire website?
Yes. 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.
What pricing plans are available, and can I make one-time lookups instead of subscribing?
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.
Do you offer annual billing?
Yes. Annual billing saves two months compared with monthly billing on every paid plan.
What happens when my API credits run out?
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.
Why am I getting timeout errors?
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.
How can my agent sign up?
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:
What's the difference between API credits and Logo Link?
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.
Do you support subdomains?
Yes, subdomains are fully supported.
Is there a free tier?
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.
How do API credits work?
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.
Are there extra fees for JS rendering, anti-bot bypass, or premium proxies?
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.
Can I crawl an entire website?
Yes. 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.
Am I billed for failed requests?
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.
What pricing plans are available, and can I make one-time lookups instead of subscribing?
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.
Which plan should I choose?
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.
Do you offer annual billing?
Yes. Annual billing saves two months compared with monthly billing on every paid plan.
Do you offer discounts for startups or nonprofits?
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.
What happens when my API credits run out?
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.
What are the rate limits, and how can I increase them?
Core API limits cap concurrent requests per organization: Free allows 1; Developer 10, Pro 100, Growth 250, and Scale 500. Accounts created before concurrency limits keep their per-minute limits, and the dashboard shows which applies. Batches, Monitors, webhook deliveries, logs, and feedback have separate organization limits. Enterprise can have custom limits; Logo Link has a separate quota.
Why am I getting timeout errors?
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.
What SDKs are available?
We provide official SDKs for TypeScript, Python, Ruby, Go, and PHP.
How can my agent sign up?
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:
When should I talk to sales?
Talk to sales if you need high-volume pricing beyond 2M credits/month, custom rate limits, SSO / SAML, SCIM provisioning, an uptime SLA, annual invoicing, an MSA / DPA, or a dedicated support channel. Reach us at hello@context.dev or through the contact page.
What's the difference between API credits and Logo Link?
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.
How fresh is the brand data? How often is it updated?
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.
Do you support subdomains?
Yes, subdomains are fully supported.
What if I need additional data points?
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.
Ship an agent that actually knows things.
Free tier, 10-minute integration, and the same API powering agents at Mintlify, daily.dev, and Propane. No credit card to start.