The go-to web data API

Context.dev turns websites into data for AI agents and applications. Scrape a page into Markdown, crawl linked pages, or extract fields into JSON shaped by your schema. When your workflow needs company context, retrieve brand profiles with logos, colors, descriptions, and social links through the same API.

Quickstart

Get an API key and make your first request with cURL or your preferred SDK.

Working with a coding agent? Follow the agent quickstart.

Try a request

Create an account, then copy your key from the dashboard. Set it in the shell where you’ll run the example:

export CONTEXT_DEV_API_KEY="ctxt_secret_..."

Choose an API, then your language.

Turn a webpage into Markdown. This request costs 1 credit.

curl --get https://api.context.dev/v1/web/scrape/markdown \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --data-urlencode "url=https://example.com" \
  --data-urlencode "useMainContentOnly=true"

import ContextDev from "context.dev";

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

const response = await client.web.webScrapeMd({
  url: "https://example.com",
  useMainContentOnly: true,
});

console.log(response.markdown);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

response = client.web.web_scrape_md(
    url="https://example.com",
    use_main_content_only=True,
)

print(response.markdown)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

response = client.web.web_scrape_md(
  url: "https://example.com",
  use_main_content_only: true,
)

puts response.markdown

package main

import (
    "context"
    "fmt"
    "os"

    contextdev "github.com/context-dot-dev/context-go-sdk/v2"
    "github.com/context-dot-dev/context-go-sdk/v2/option"
    "github.com/context-dot-dev/context-go-sdk/v2/packages/param"
)

func main() {
    client := contextdev.NewClient(option.WithAPIKey(os.Getenv("CONTEXT_DEV_API_KEY")))
    response, err := client.Web.WebScrapeMd(context.Background(), contextdev.WebWebScrapeMdParams{
        URL:                "https://example.com",
        UseMainContentOnly: param.NewOpt(true),
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(response.Markdown)
}

<?php

require __DIR__.'/vendor/autoload.php';

$client = new ContextDev\Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$response = $client->web->webScrapeMd(
    url: "https://example.com",
    useMainContentOnly: true,
);

echo $response->markdown, PHP_EOL;

Read page text from markdown. The Markdown guide covers content filters and freshness.

Extract a company fact into your JSON Schema, using up to 5 relevant pages. The 10-credit charge covers the full extraction, not each page.

curl https://api.context.dev/v1/web/extract \
  --request POST \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "url": "https://stripe.com",
    "schema": {
      "type": "object",
      "properties": {
        "founded_year": {
          "type": ["integer", "null"],
          "description": "The year the company says it was founded. Return null if not stated."
        }
      },
      "required": ["founded_year"],
      "additionalProperties": false
    },
    "maxPages": 5,
    "factCheck": true
  }'

import ContextDev from "context.dev";

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

const response = await client.web.extract({
  url: "https://stripe.com",
  schema: {
    type: "object",
    properties: {
      founded_year: {
        type: ["integer", "null"],
        description:
          "The year the company says it was founded. Return null if not stated.",
      },
    },
    required: ["founded_year"],
    additionalProperties: false,
  },
  maxPages: 5,
  factCheck: true,
});

console.log(response.data, response.urls_analyzed);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

response = client.web.extract(
    url="https://stripe.com",
    schema={
      "type": "object",
      "properties": {
        "founded_year": {
          "type": ["integer", "null"],
          "description": "The year the company says it was founded. Return null if not stated.",
        },
      },
      "required": ["founded_year"],
      "additionalProperties": False,
    },
    max_pages=5,
    fact_check=True,
)

print(response.data, response.urls_analyzed)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

response = client.web.extract(
  url: "https://stripe.com",
  schema: {
    "type" => "object",
    "properties" => {
      "founded_year" => {
        "type" => ["integer", "null"],
        "description" => "The year the company says it was founded. Return null if not stated.",
      },
    },
    "required" => ["founded_year"],
    "additionalProperties" => false,
  },
  max_pages: 5,
  fact_check: true,
)

pp response.data, response.urls_analyzed

package main

import (
    "context"
    "fmt"
    "os"

    contextdev "github.com/context-dot-dev/context-go-sdk/v2"
    "github.com/context-dot-dev/context-go-sdk/v2/option"
    "github.com/context-dot-dev/context-go-sdk/v2/packages/param"
)

func main() {
    client := contextdev.NewClient(option.WithAPIKey(os.Getenv("CONTEXT_DEV_API_KEY")))
    response, err := client.Web.Extract(context.Background(), contextdev.WebExtractParams{
        URL: "https://stripe.com",
        Schema: map[string]any{
            "type": "object",
            "properties": map[string]any{
                "founded_year": map[string]any{
                    "type":        []string{"integer", "null"},
                    "description": "The year the company says it was founded. Return null if not stated.",
                },
            },
            "required":             []string{"founded_year"},
            "additionalProperties": false,
        },
        MaxPages:  param.NewOpt(int64(5)),
        FactCheck: param.NewOpt(true),
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(response.Data, response.URLsAnalyzed)
}

<?php

require __DIR__.'/vendor/autoload.php';

$client = new ContextDev\Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$response = $client->web->extract(
    url: "https://stripe.com",
    schema: [
      "type" => "object",
      "properties" => [
        "founded_year" => [
          "type" => ["integer", "null"],
          "description" => "The year the company says it was founded. Return null if not stated.",
        ],
      ],
      "required" => ["founded_year"],
      "additionalProperties" => false,
    ],
    maxPages: 5,
    factCheck: true,
);

print_r([$response->data, $response->urlsAnalyzed]);

Read the extracted object from data and its source pages from urls_analyzed. See the extraction guide for schema design and fact checks.

Find image sources referenced by a webpage. This request costs 1 credit.

curl --get https://api.context.dev/v1/web/scrape/images \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --data-urlencode "url=https://stripe.com"

import ContextDev from "context.dev";

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

const page = await client.web.webScrapeImages({
  url: "https://stripe.com",
});

console.log(page.images);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

page = client.web.web_scrape_images(url="https://stripe.com")
print(page.images)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

page = client.web.web_scrape_images(url: "https://stripe.com")
puts page.images

package main

import (
    "context"
    "fmt"
    "os"

    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(os.Getenv("CONTEXT_DEV_API_KEY")),
    )

    page, err := client.Web.WebScrapeImages(context.Background(), contextdev.WebWebScrapeImagesParams{
        URL: "https://stripe.com",
    })
    if err != nil {
        panic(err)
    }

    fmt.Println(page.Images)
}

<?php

require __DIR__.'/vendor/autoload.php';

use ContextDev\Client;

$client = new Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$page = $client->web->webScrapeImages(url: 'https://stripe.com');
print_r($page->images);

The images array contains the discovered assets; it may be empty. See the image guide for dimensions, hosted copies, and visual classification.

List up to 50 customer-page URLs from Stripe’s public sitemaps without rendering each page. This request costs 1 credit.

curl --get https://api.context.dev/v1/web/scrape/sitemap \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --data-urlencode "domain=stripe.com" \
  --data-urlencode "maxLinks=50" \
  --data-urlencode "urlRegex=/customers/"

import ContextDev from "context.dev";

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

const sitemap = await client.web.webScrapeSitemap({
  domain: "stripe.com",
  maxLinks: 50,
  urlRegex: "/customers/",
});

console.log(sitemap.urls);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

sitemap = client.web.web_scrape_sitemap(
    domain="stripe.com",
    max_links=50,
    url_regex="/customers/",
)

print(sitemap.urls)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

sitemap = client.web.web_scrape_sitemap(
  domain: "stripe.com",
  max_links: 50,
  url_regex: "/customers/",
)

puts sitemap.urls

package main

import (
    "context"
    "fmt"
    "os"

    contextdev "github.com/context-dot-dev/context-go-sdk/v2"
    "github.com/context-dot-dev/context-go-sdk/v2/option"
    "github.com/context-dot-dev/context-go-sdk/v2/packages/param"
)

func main() {
    client := contextdev.NewClient(
        option.WithAPIKey(os.Getenv("CONTEXT_DEV_API_KEY")),
    )

    sitemap, err := client.Web.WebScrapeSitemap(context.Background(), contextdev.WebWebScrapeSitemapParams{
        Domain: "stripe.com",
        MaxLinks: param.NewOpt[int64](50),
        URLRegex: param.NewOpt("/customers/"),
    })
    if err != nil {
        panic(err)
    }

    fmt.Println(sitemap.URLs)
}

<?php

require __DIR__.'/vendor/autoload.php';

use ContextDev\Client;

$client = new Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$sitemap = $client->web->webScrapeSitemap(
    domain: 'stripe.com',
    maxLinks: 50,
    urlRegex: '/customers/',
);

print_r($sitemap->urls);

Read the URL list from urls and check meta for sitemap fetches and errors. The sitemap guide covers filtering and discovery limits.

Look up a company profile with logos, colors, descriptions, and social links. A successful lookup costs 10 credits.

curl https://api.context.dev/v1/brand/retrieve \
  --request POST \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "type": "by_domain",
    "domain": "stripe.com"
  }'

import ContextDev from "context.dev";

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

const response = await client.brand.retrieve({
  type: "by_domain",
  domain: "stripe.com",
});

console.log(response.brand?.title);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

response = client.brand.retrieve(
    type="by_domain",
    domain="stripe.com",
)

print(response.brand.title if response.brand else None)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

response = client.brand.retrieve(
  body: {
    "type" => "by_domain",
    "domain" => "stripe.com",
  }
)

puts response.brand&.title

package main

import (
    "context"
    "fmt"
    "os"

    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(os.Getenv("CONTEXT_DEV_API_KEY")))
    response, err := client.Brand.Get(context.Background(), contextdev.BrandGetParams{
        OfByDomain: &contextdev.BrandGetParamsBodyByDomain{
            Domain: "stripe.com",
        },
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(response.Brand.Title)
}

<?php

require __DIR__.'/vendor/autoload.php';

$client = new ContextDev\Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

// Use the SDK's low-level request: its generated Brand helper cannot express this lookup.
$response = $client->request(
    method: 'post',
    path: 'brand/retrieve',
    body: [
      "type" => "by_domain",
      "domain" => "stripe.com",
    ],
);
$data = json_decode((string) $response->getBody(), true, flags: JSON_THROW_ON_ERROR);
echo $data['brand']['title'] ?? 'No match', PHP_EOL;

The matched company is in brand. PHP SDK 2.14.0 uses its low-level request method for this lookup. See the brand guide for lookup options and result fields.

Extract observed colors, typography, and component styles. This request costs 10 credits.

curl --get https://api.context.dev/v1/web/styleguide \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --data-urlencode "domain=stripe.com" \
  --data-urlencode "colorScheme=light"

import ContextDev from "context.dev";

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

const response = await client.web.extractStyleguide({
  domain: "stripe.com",
  colorScheme: "light",
});

console.log(response.styleguide?.colors);
console.log(response.styleguide?.typography.headings.h1);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

response = client.web.extract_styleguide(
    domain="stripe.com",
    color_scheme="light",
)

print(response.styleguide.colors)
print(response.styleguide.typography.headings.h1)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(
  api_key: ENV.fetch("CONTEXT_DEV_API_KEY")
)

response = client.web.extract_styleguide(
  domain: "stripe.com",
  color_scheme: :light
)

puts response.styleguide.colors.inspect
puts response.styleguide.typography.headings.h1.inspect

package main

import (
    "context"
    "fmt"
    "os"

    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(os.Getenv("CONTEXT_DEV_API_KEY")),
    )

    response, err := client.Web.ExtractStyleguide(
        context.Background(),
        contextdev.WebExtractStyleguideParams{
            Domain: contextdev.String("stripe.com"),
            ColorScheme: contextdev.WebExtractStyleguideParamsColorSchemeLight,
        },
    )
    if err != nil {
        panic(err)
    }

    fmt.Println(response.Styleguide.Colors)
    fmt.Println(response.Styleguide.Typography.Headings.H1)
}

<?php

require __DIR__.'/vendor/autoload.php';

use ContextDev\Client;

$client = new Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$response = $client->web->extractStyleguide(
    domain: 'stripe.com',
    colorScheme: 'light',
);

var_dump($response->styleguide->colors);
var_dump($response->styleguide->typography->headings->h1);

Inspect styleguide.colors and styleguide.typography. These are observations of the rendered page, not an official design-system specification. See the styleguide guide for the full result.

Submit two URLs for background scraping. Each successful page costs 1 credit.

curl https://api.context.dev/v1/batch/submit \
  --request POST \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "input": {
    "mode": "scrape",
    "data": {
      "format": "markdown",
      "urls": [
        {
          "url": "https://docs.context.dev/introduction"
        },
        {
          "url": "https://docs.context.dev/quickstart"
        }
      ]
    }
  }
}'

import ContextDev from "context.dev";

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

const response = await client.batch.submit({
  input: {
    mode: "scrape",
    data: {
      format: "markdown",
      urls: [
        {
          url: "https://docs.context.dev/introduction",
        },
        {
          url: "https://docs.context.dev/quickstart",
        },
      ],
    },
  },
});
console.log(response.id);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

response = client.batch.submit(
    input={
        "mode": "scrape",
        "data": {
            "format": "markdown",
            "urls": [
                {
                    "url": "https://docs.context.dev/introduction",
                },
                {
                    "url": "https://docs.context.dev/quickstart",
                },
            ],
        },
    },
)
print(response.id)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

response = client.batch.submit(
  input: {
    mode: "scrape",
    data: {
      format: "markdown",
      urls: [
        {
          url: "https://docs.context.dev/introduction",
        },
        {
          url: "https://docs.context.dev/quickstart",
        },
      ],
    },
  },
)
puts response.id

package main

import (
    "context"
    "fmt"
    "os"

    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(os.Getenv("CONTEXT_DEV_API_KEY")))

    response, err := client.Batch.Submit(context.Background(), contextdev.BatchSubmitParams{
        Input: contextdev.BatchSubmitParamsInputUnion{
            OfScrape: &contextdev.BatchSubmitParamsInputScrape{
                Mode: "scrape",
                Data: contextdev.BatchSubmitParamsInputScrapeDataUnion{
                    OfMarkdown: &contextdev.BatchSubmitParamsInputScrapeDataMarkdown{
                        Format: "markdown",
                        URLs: []contextdev.BatchSubmitParamsInputScrapeDataMarkdownURL{
                            contextdev.BatchSubmitParamsInputScrapeDataMarkdownURL{
                                URL: "https://docs.context.dev/introduction",
                            },
                            contextdev.BatchSubmitParamsInputScrapeDataMarkdownURL{
                                URL: "https://docs.context.dev/quickstart",
                            },
                        },
                    },
                },
            },
        },
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(response.ID)
}

<?php
require __DIR__.'/vendor/autoload.php';

use ContextDev\Client;

$client = new Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$response = $client->batch->submit(
    input: [
        "mode" => "scrape",
        "data" => [
            "format" => "markdown",
            "urls" => [
                [
                    "url" => "https://docs.context.dev/introduction",
                ],
                [
                    "url" => "https://docs.context.dev/quickstart",
                ],
            ],
        ],
    ],
);
echo $response->id, PHP_EOL;

The response contains a job id, not completed page content. Save it, then poll for completion and read the results.

Check a pricing page for text changes every day. No webhook is required.

This creates an ongoing monitor. Its initial and scheduled runs consume credits. Pause or delete it when you finish testing.

curl https://api.context.dev/v1/monitors \
  --request POST \
  --header "Authorization: Bearer $CONTEXT_DEV_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "name": "Pricing changes",
  "target": {
    "type": "page",
    "url": "https://stripe.com/pricing",
    "normalize_whitespace": true
  },
  "change_detection": {
    "type": "exact"
  },
  "schedule": {
    "type": "interval",
    "frequency": 1,
    "unit": "days"
  }
}'

import ContextDev from "context.dev";

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

const response = await client.monitors.create({
  name: "Pricing changes",
  target: {
    type: "page",
    url: "https://stripe.com/pricing",
    normalize_whitespace: true,
  },
  change_detection: {
    type: "exact",
  },
  schedule: {
    type: "interval",
    frequency: 1,
    unit: "days",
  },
});
console.log(response.id, response.initial_run_id);

import os
from context.dev import ContextDev

client = ContextDev(api_key=os.environ["CONTEXT_DEV_API_KEY"])

response = client.monitors.create(
    name="Pricing changes",
    target={
        "type": "page",
        "url": "https://stripe.com/pricing",
        "normalize_whitespace": True,
    },
    change_detection={
        "type": "exact",
    },
    schedule={
        "type": "interval",
        "frequency": 1,
        "unit": "days",
    },
)
print(response.id, response.initial_run_id)

require "cgi/core"
require "context_dev"

client = ContextDev::Client.new(api_key: ENV.fetch("CONTEXT_DEV_API_KEY"))

response = client.monitors.create(
  name: "Pricing changes",
  target: {
    type: "page",
    url: "https://stripe.com/pricing",
    normalize_whitespace: true,
  },
  change_detection: {
    type: "exact",
  },
  schedule: {
    type: "interval",
    frequency: 1,
    unit: "days",
  },
)
puts response.id, response.initial_run_id

package main

import (
    "context"
    "fmt"
    "os"

    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(os.Getenv("CONTEXT_DEV_API_KEY")))

    response, err := client.Monitors.New(context.Background(), contextdev.MonitorNewParams{
        Name: "Pricing changes",
        Target: contextdev.MonitorNewParamsTargetUnion{
            OfPage: &contextdev.MonitorNewParamsTargetPage{
                Type:                "page",
                URL:                 "https://stripe.com/pricing",
                NormalizeWhitespace: contextdev.Bool(true),
            },
        },
        ChangeDetection: contextdev.MonitorNewParamsChangeDetectionUnion{
            OfExact: &contextdev.MonitorNewParamsChangeDetectionExact{
                Type: "exact",
            },
        },
        Schedule: contextdev.MonitorNewParamsSchedule{
            Type:      "interval",
            Frequency: 1,
            Unit:      "days",
        },
    })
    if err != nil {
        panic(err)
    }
    fmt.Println(response.ID, response.InitialRunID)
}

<?php
require __DIR__.'/vendor/autoload.php';

use ContextDev\Client;

$client = new Client(apiKey: getenv('CONTEXT_DEV_API_KEY'));

$response = $client->monitors->create(
    name: "Pricing changes",
    target: [
        "type" => "page",
        "url" => "https://stripe.com/pricing",
        "normalizeWhitespace" => true,
    ],
    changeDetection: [
        "type" => "exact",
    ],
    schedule: [
        "type" => "interval",
        "frequency" => 1,
        "unit" => "days",
    ],
);
echo $response->id, " ", $response->initialRunID, PHP_EOL;

Save id and initial_run_id. The first run establishes a baseline. Use the monitoring guide to read later runs and changes.

The quickstart covers SDK installation, run commands, and how to check each result.

Explore the APIs

Web data APIs

Scrape Markdown

Turn a webpage into Markdown for agents, search, and retrieval.

Scrape HTML

Retrieve page HTML to parse and process yourself.

Structured extraction

Combine fields from relevant pages into one object matching your JSON Schema.

Crawl

Follow website links and return each page as Markdown.

Web search

Search the web and optionally scrape result pages in the same call.

Sitemap

Discover URLs in public sitemaps before fetching page content.

Images

Extract image assets from a webpage, with optional metadata enrichment.

Screenshots

Capture a webpage as an image.

Document parsing

Convert PDFs, Office documents, images, and other supported files into Markdown.

Brand data APIs

Brand lookup

Retrieve company logos, colors, descriptions, social links, and industry tags where available.

Brand search

Find indexed brands by name or domain prefix for autocomplete.

Simplified brand data

Get a smaller brand response with a domain, title, colors, logos, and backdrops.

Styleguide

Extract a website’s colors, typography, spacing, and component styles.

Fonts

Identify a website’s font families, fallbacks, and usage.

Logo Link

Embed a company logo directly using a separate public client ID.

NAICS classification

Classify a company using 2022 NAICS industry codes.

SIC classification

Classify a company using original SIC codes or the SEC’s current list.

Company and product data

Product extraction

Extract pricing, images, descriptions, and other details from one product page.

Product discovery

Discover and extract up to 12 products from a website. Available in beta.

People enrichment

Match identity clues to a person profile with a match score. Beta, paid plans.

Company news

Find current and historical company news by name, domain, ticker, or ISIN.

Company funding

Retrieve known funding rounds, dates, and amounts by company domain.

Automation and utilities

Batches

Process URL lists or website crawls asynchronously and retrieve the results.

Monitors

Track changes to pages, sitemaps, or structured data and receive signed webhooks.

Prefetch

Warm brand or styleguide caches before you need the data. Paid subscription required.

Before you ship

Context.dev is a hosted API, with SDKs for TypeScript, Python, Ruby, Go, and PHP. There is no self-hosted edition. Scraping can render JavaScript, but a login wall or bot challenge can still prevent access. Markdown results may come from a cache up to one day old by default; set maxAgeMs=0 when you need a new fetch. Other endpoints have their own freshness rules. Each guide explains its costs, limits, and failure cases.

API reference

Check the request parameters and response fields for each endpoint.

Production checklist

Plan retries, data handling, and deployment behavior.

Quickstart

​Try a request

​Explore the APIs

​Web data APIs

Scrape Markdown

Scrape HTML

Structured extraction

Crawl

Web search

Sitemap

Images

Screenshots

Document parsing

​Brand data APIs

Brand lookup

Brand search

Simplified brand data

Styleguide

Fonts

Logo Link

NAICS classification

SIC classification

​Company and product data

Product extraction

Product discovery

People enrichment

Company news

Company funding

​Automation and utilities

Batches

Monitors

Prefetch

​Before you ship

API reference

Production checklist

Try a request

Explore the APIs

Web data APIs

Brand data APIs

Company and product data

Automation and utilities

Before you ship