The Internet's Context {API}

One API. Every piece of web context your agent needs.

https://
No credit card required
Book Demo

Powering agents and products at

For AI Companies

One API
Infinite Use Cases

Retrieve, extract, classify, and enrich web data in seconds.

Extract web content
import ContextDev from 'context.dev';

const client = new ContextDev({ apiKey: process.env['CONTEXT_DEV_API_KEY'] });

// Get clean markdown from any page
const { markdown } = await client.web.webScrapeMd({
  url: 'https://openai.com/pricing'
});

// Get fully rendered HTML (JS executed)
const { html } = await client.web.webScrapeHTML({
  url: 'https://react.dev/learn'
});

// Extract all images from a page
const { images } = await client.web.webScrapeImages({
  url: 'https://dribbble.com/shots/popular'
});

// Crawl an entire site → markdown for every page
const { results, metadata } = await client.web.webCrawlMd({
  url: 'https://docs.stripe.com',
  maxPages: 50,
  maxDepth: 3,
  useMainContentOnly: true
});
Connect Your Agent To The Web

What your agent can
do with context.dev.

You have an agent. Here's what it can do now.

Read the web, live

Give an agent real-time access to any page. Scrape to markdown, render JS, extract images, so the agent reasons over the current web, not a frozen snapshot.

Agent: I need to check their pricing page.

Request

GET /v1/scrape/markdown

{ url: "vercel.com/pricing" }

Response · Markdown247ms

# Vercel Pricing

Develop. Preview. Ship. Start free and

scale to the enterprise.

## Hobby $0/mo

For personal projects and experiments.

## Pro $20/mo

For teams building production apps.

Agent: Their Pro plan is $20/mo, includes...

Ground RAG in fresh content

Keep your retrieval index current. Crawl a sitemap, convert every page to clean markdown, and pipe it straight into embeddings, with no brittle parsers in between.

acme.com/docs/api/auth
acme.com/blog/release-v3
acme.com/pricing
acme.com/changelog
acme.com/docs/sdk
markdown + embed
Knowledge Base5 docs indexed

Run deep research on demand

Answer "tell me about this company" with actual sources. Resolve a domain to a typed profile, then expand with custom AI queries pulled from the live site.

Input
notion.com
?
No data
Enriched
Notion

Notion

San Francisco, CA
IndustrySoftware (B2B)
Employees~1,000
Revenue$600M ARR
Founded2013
Valuation$11B
xlinkedinig

Personalize onboarding in a call

Make a new user feel seen from sign-up. One domain → company name, logo, colors, industry, auto-filled before they tab away.

linear.app
Auto-fill
Company Name
Linear
Industry
Developer Tools
Brand Color
#5E6AD2
Description
Issue tracking for modern teams
Logo
linear.applinear-logo.svg

Enrich any entity your agent sees

Turn the references in your prompts into structured data. One call hydrates a company reference with logos, colors, industry, socials, and firmographics.

Y Combinator

Y Combinator

ycombinator.com

Startup accelerator investing $500K in early-stage companies.

IndustryInvestment & WealthTech
SloganFunding the future
Founded2005
LocationSan Francisco, CA
xlinkedinyoutube

Make sense of transaction noise

Resolve "SQ *BLUE BOTTLE 8xx" into Blue Bottle Coffee. Identify the brand, attach visuals and metadata, hand the agent something it can actually act on.

AMZN MKTP US*2K8F7G1
amazon.com

Amazon

E-commerce

SQ *BLUE BOTTLE COF
bluebottlecoffee.com

Blue Bottle

Food & Drink

GITHUB.COM 2FA8X91
github.com

GitHub

Developer Tools

The Problem

Your agent is only as good as what it knows.

Most agent failures aren’t reasoning failures. They’re context failures. The agent didn’t have the right data, in the right shape, at the right time.

  1. 01

    Training data is frozen.

    Your model knows the web as of some cutoff. The web your user is asking about is newer than that, every time.

  2. 02

    Generic scrapers return noise.

    Raw HTML with nav, ads, and boilerplate forces your agent to guess. Tokens get burned on chrome, not signal.

  3. 03

    Entities need structure, not prose.

    An agent asked about a company shouldn't read a blog post about it. It needs logos, colors, industry, socials, already typed.

One platform · three surfaces

The context your agent
can't get anywhere else.

Markdown from the live web, typed brand data on any company, and a one-line logo embed, all from the same API.

Web Extraction

Read the live web as markdown.

Clean, LLM-ready markdown from any URL, with crawl, sitemap, AI extraction, and product pipelines on the same primitive.

https://openai.com/pricing
Request
await client.web.webScrapeMd({
  url: 'https://openai.com/pricing'
})
Response · markdown247ms

# OpenAI Pricing

Simple, predictable pricing across models.

## GPT-5 $10/1M

Most capable model for complex tasks.

## GPT-5 mini $0.5/1M

Fast and affordable for most tasks.

- Context window: 400k tokens

Brand Intelligence

Any domain, typed.

Resolve a domain, email, ticker, or messy merchant descriptor into a typed company with logos, colors, fonts, and firmographics.

Linear

Linear

linear.app

Purpose-built issue tracking and project planning for modern software teams.

IndustryDeveloper Tools
SloganBuilt for modern teams
Founded2019
LocationSan Francisco, CA
xlinkedingithub
Logo Link

One <img> tag. Any logo.

No API call. No SDK. No backend. Just an image URL, with logos served from a global CDN in ~20ms.

HTML
<img src="https://logos.context.dev?domain=example.com"/>
stripe.com
linear.app
notion.so
github.com
figma.com
shopify.com
vercel.com
openai.com
anthropic.com
slack.com
discord.com
context.dev
5K+ Developers

What developers say

Feedback from the engineers shipping with Context.dev every day.

John Acosta

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

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

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

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

Vlad Veselukha

Vlad Veselukha

Context.dev offers extensive documentation making the setup super easy. On top of this, there is a dedicated Slack channel in case you have follow-up questions. Overall the API integration process was very smooth.

Senior Data Engineer @ Vizzy

CUSTOMER STORIES

See how
our customers do it

From scrappy startups to Fortune 500s, teams ship brand-powered features in days instead of quarters.

Latest
Blog Posts

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, Context.dev offers a free tier with 500 API credits and 10K Logo Link requests to test out both services.
What's the difference between API credits and Logo Link?
They are two separate products with separate quotas. API credits are used to call any endpoint — brand data, logos, colors, fonts, and web scraping. Logo Link is a simpler service that returns just the square logo via a direct URL for displaying in your app. Logo Link has no rate limits and much higher quotas, while API credits have rate limits (calls per second) that vary by plan.
How do API credits work?
API credits are consumed whenever you call our endpoints. Brand API calls (logo retrieval, color extraction, font detection, brand profiles, prefetch) cost 10 credits per call. Web endpoints (scraping) cost 1 credit per call. Logo Link requests are counted separately and do not use your API credits.
What pricing plans are available, and can I make one-time lookups instead of subscribing?
Context.dev offers several pricing tiers including Starter, Pro, and Scale plans with monthly API credit allowances. 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 discounts for startups or nonprofits?
Yes! We offer a startup discount of up to 30% off for one year if you're still early-stage. Apply at https://www.context.dev/startup-discount
What happens when my API credits run out?
Each plan includes a monthly API credit allowance that replenishes automatically at the start of each billing cycle. When your credits are depleted, API calls will return a 401 error. You can configure auto top-up in your dashboard settings to avoid interruptions. Logo Link has a separate quota and is not affected when API credits run out.
What are the rate limits, and how can I increase them?
Rate limits apply only to API calls, not Logo Link. Rate limits vary by plan: Free tier has 1 call/second, Starter has 2 calls/second, Pro has 5 calls/second, and Scale has 20 calls/second. Logo Link has no rate limits. Contact us to discuss higher rate limits for your use case.
Why am I getting timeout errors?
First-time domain lookups may take 10-30 seconds as we crawl and process the website. For time-sensitive applications, use the Prefetch endpoint to request brand data in advance, increase your client-side timeout to at least 30 seconds, or implement async/polling patterns for batch operations. Approximately 70% of requests hit cached brands, which return much faster.
How fresh is the brand data? How often is it updated?
Cached brand data is refreshed quarterly by default. Any brand older than 3 months is completely re-fetched when requested via the API. You can request a manual refresh for specific domains using our brand update form at https://www.context.dev/update. Image/logo URLs are guaranteed to remain valid for up to 1 year.
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.
What SDKs are available?
We provide official SDKs for TypeScript, Python, and Ruby.

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.