Introducing Highlights: the context that matters

Deep research API. Get answers you can use.

Give your agent a research question. Get structured findings in your chosen shape, with source URLs it can cite and verify.

Get API key View documentation

What are Linear’s main product features?

mode: fast

Ask

Your shape

json_format

{
  "features": [""]
}

Answer

json_content

{
  "features": [
    "Issue tracking",
    "Project planning",
    "Product roadmaps"
  ]
}

Sources

Linear

linear.app

Features

linear.app/features

View sources

Research task · Structured answer

Backed by Y Combinator. Teams build with Context.dev.

per answer in Fast mode: 10 credits
per answer in Ultra mode: 100 credits
shape for every answer: Your JSON
returned with every answer: Sources

Start with a question: Describe the research task instead of assembling a set of pages by hand.
Choose the structure: Define the JSON shape your product needs, so the result can move straight into your workflow.
Keep the sources: Use the returned page URLs to show your users where the answer came from.

Your question. Your output shape.

Send a task and an example JSON structure. The response includes the structured answer and the URLs used as evidence.

$ npm install context.dev

Read the API reference

answers.ts

import ContextDev from 'context.dev';

const client = new ContextDev({ apiKey: 'YOUR_API_KEY' });

const answer = await client.web.answers({
  task: 'Find the main product features on linear.app.',
  mode: 'fast',
  json_format: {
    features: [''],
  },
});

console.log(answer.json_content);
console.log(answer.sources);

from context.dev import ContextDev

client = ContextDev(api_key="YOUR_API_KEY")

response = client.web.answers(
    task="Find the main product features on linear.app.",
    mode="fast",
    json_format={"features": [""]},
)
print(response)

require "context_dev"

client = ContextDev::Client.new(api_key: "YOUR_API_KEY")

response = client.web.answers(
  task: "Find the main product features on linear.app.",
  mode: :fast,
  json_format: { "features" => [""] }
)
puts response

<?php

require_once 'vendor/autoload.php';

use ContextDev\Client;

$client = new Client(apiKey: 'YOUR_API_KEY');

$response = $client->web->answers(
    task: 'Find the main product features on linear.app.',
    jsonFormat: ['features' => ['']],
    mode: 'fast',
);

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.Answers(context.TODO(), contextdev.WebAnswersParams{
		Task:       "Find the main product features on linear.app.",
		Mode:       contextdev.WebAnswersParamsModeFast,
		JsonFormat: map[string]any{"features": []any{""}},
	})
	if err != nil {
		panic(err)
	}

	fmt.Printf("%+v\n", response)
}

curl -X POST "https://api.context.dev/v1/web/answers" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "task": "Find the main product features on linear.app.",
  "mode": "fast",
  "json_format": {
    "features": [
      ""
    ]
  }
}'

Give your agents a research capability.

Move from a question to sourced findings that your application can work with.

Run deep research on demand

Answer “tell me about this company” with actual sources. Resolve a domain to a typed profile, then expand with schema-based extraction from the live site.

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

markdown → your embeddings

Knowledge base

4 docs indexed

A few things to know.

Start with your next request.

One API key for scraping, research, brand data, batches, and monitoring.

Get API key View documentation