Exa Contents Fetch
Fetches content from web pages and documents using Exa.
Offering
- Provider
- api.exa.ai
- Method
- POST
- Offering type
- Api Endpoint
- Transport type
- http
- Category
- Web Search Research
- Delivery
- Not provided
- Pricing model
- Not provided
- x402 version
- 2
Endpoint context
- URL
https://api.exa.ai/contents- MIME type
- application/json
- First seen
- 2026-10-16T01:50:03.310Z
- Last seen
- Tags
- Search, AI, Web, Research, X402, Exa, ai-search, web-search, contents, content-retrieval
Payment pricing
x402 payment terms are the authoritative price for calling this endpoint.
- Payment option 1
- 0.001 USDC
Atomic price: 1000 · Network: eip155:8453 · Asset: USDC · Scheme: exact - Payment option 2
- 0.001 USDC
Atomic price: 1000 · Network: solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp · Asset: USDC · Scheme: exact - Payment option 3
- 0.001 USDC
Atomic price: 1000 · Network: eip155:8453 · Asset: USDC · Scheme: exact - Payment option 4
- 0.001 USDC
Atomic price: 1000 · Network: eip155:480 · Asset: USDC · Scheme: exact - Payment option 5
- 1000 atomic units
Atomic price: 1000 · Network: eip155:5042 · Asset: 0x3600000000000000000000000000000000000000 · Scheme: exact - Payment option 6
- 1000 atomic units
Atomic price: 1000 · Network: eip155:5042 · Asset: 0x3600000000000000000000000000000000000000 · Scheme: exact - Payment option 7
- 0.001 USDC
Atomic price: 1000 · Network: eip155:8453 · Asset: USDC · Scheme: exact
Raw x402 terms
[
{
"scheme": "exact",
"network": "eip155:8453",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "1000",
"payTo": "0x6d6E695b09861467c7d462f5AAF31cF3540B9192"
},
{
"scheme": "exact",
"network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp",
"asset": "EPjFWdd5AufqSSqeM2qN1xzybapC8G4wEGGkZwyTDt1v",
"amount": "1000",
"payTo": "12Ec2cJmfR1C9uwejzxcuMhUgEC7wDrLgm1wBvvR5w9E"
},
{
"scheme": "exact",
"network": "eip155:8453",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "1000",
"payTo": "0xB98eF29eb2be19Ae646A8FC0248255B90A332dbC"
},
{
"scheme": "exact",
"network": "eip155:480",
"asset": "0x79A02482A880bCE3F13e09Da970dC34db4CD24d1",
"amount": "1000",
"payTo": "0xB98eF29eb2be19Ae646A8FC0248255B90A332dbC"
},
{
"scheme": "exact",
"network": "eip155:5042",
"asset": "0x3600000000000000000000000000000000000000",
"amount": "1000",
"payTo": "0xB98eF29eb2be19Ae646A8FC0248255B90A332dbC"
},
{
"scheme": "exact",
"network": "eip155:5042",
"asset": "0x3600000000000000000000000000000000000000",
"amount": "1000",
"payTo": "0xB98eF29eb2be19Ae646A8FC0248255B90A332dbC"
},
{
"scheme": "exact",
"network": "eip155:8453",
"asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
"amount": "1000",
"payTo": "0xB98eF29eb2be19Ae646A8FC0248255B90A332dbC"
}
]Observed health
- Status
- Healthy
- Latest latency
- 96 ms
- Average latency
- 241 ms
- HTTP status
- 204
- Last checked
- Reachability
- 100% over 14 checks
Latency is measured to the first response headers. A reachable result does not verify response accuracy or merchant identity.
Input schema
{
"body": {
"type": "object",
"allOf": [
{
"type": "object",
"required": [
"urls"
],
"properties": {
"ids": {
"type": "array",
"items": {
"type": "string"
},
"example": [
"https://arxiv.org/pdf/2307.06435"
],
"deprecated": true,
"description": "Deprecated - use 'urls' instead. Array of document IDs obtained from searches."
},
"urls": {
"type": "array",
"items": {
"type": "string"
},
"example": [
"https://arxiv.org/pdf/2307.06435"
],
"description": "Array of URLs to crawl (backwards compatible with 'ids' parameter)."
}
}
},
{
"type": "object",
"properties": {
"text": {
"oneOf": [
{
"type": "boolean",
"title": "Simple text retrieval",
"description": "If true, returns full page text with default settings. If false, disables text return."
},
{
"type": "object",
"title": "Advanced text options",
"properties": {
"verbosity": {
"enum": [
"compact",
"standard",
"full"
],
"type": "string",
"default": "compact",
"example": "standard",
"description": "Controls the verbosity level of returned content. Requires livecrawl: \"always\" to take effect.\n- compact: Most concise output, main content only (default)\n- standard: Balanced content with more detail\n- full: Complete content including all sections\n"
},
"maxCharacters": {
"type": "integer",
"example": 1000,
"description": "Maximum character limit for the full page text. Useful for controlling response size and API costs."
},
"excludeSections": {
"type": "array",
"items": {
"enum": [
"header",
"navigation",
"banner",
"body",
"sidebar",
"footer",
"metadata"
],
"type": "string"
},
"example": [
"navigation",
"footer",
"sidebar"
],
"description": "Exclude content from these semantic page sections. Requires livecrawl: \"always\" to take effect.\n"
},
"includeHtmlTags": {
"type": "boolean",
"default": false,
"example": false,
"description": "Include HTML tags in the response, which can help LLMs understand text structure and formatting."
},
"includeSections": {
"type": "array",
"items": {
"enum": [
"header",
"navigation",
"banner",
"body",
"sidebar",
"footer",
"metadata"
],
"type": "string"
},
"example": [
"body",
"header"
],
"description": "Only include content from these semantic page sections. Requires livecrawl: \"always\" to take effect.\n"
}
},
"description": "Advanced options for controlling text extraction. Use this when you need to limit text length or include HTML structure."
}
]
},
"extras": {
"type": "object",
"properties": {
"links": {
"type": "integer",
"default": 0,
"example": 1,
"description": "Number of URLs to return from each webpage."
},
"imageLinks": {
"type": "integer",
"default": 0,
"example": 1,
"description": "Number of images to return for each result."
}
},
"description": "Extra parameters to pass."
},
"context": {
"oneOf": [
{
"type": "boolean",
"example": true,
"deprecated": true,
"description": "Deprecated: Use highlights or text instead. Returns page contents as a combined context string."
},
{
"type": "object",
"deprecated": true,
"properties": {
"maxCharacters": {
"type": "integer",
"example": 10000,
"description": "Deprecated. Maximum character limit for the context string."
}
},
"description": "Deprecated: Use highlights or text instead. Returns page contents as a combined context string."
}
]
},
"summary": {
"type": "object",
"properties": {
"query": {
"type": "string",
"example": "Main developments",
"description": "Custom query for the LLM-generated summary."
},
"schema": {
"type": "object",
"example": {
"type": "object",
"title": "Title",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"Property 1"
],
"properties": {
"Property 1": {
"type": "string",
"description": "Description"
},
"Property 2": {
"enum": [
"option 1",
"option 2",
"option 3"
],
"type": "string",
"description": "Description"
}
}
},
"description": "JSON schema for structured output from summary. \nSee https://json-schema.org/overview/what-is-jsonschema for JSON Schema documentation.\n"
}
},
"description": "Summary of the webpage"
},
"subpages": {
"type": "integer",
"default": 0,
"example": 1,
"description": "The number of subpages to crawl. The actual number crawled may be limited by system constraints."
},
"livecrawl": {
"enum": [
"never",
"fallback",
"preferred",
"always"
],
"type": "string",
"example": "preferred",
"deprecated": true,
"description": "**Deprecated**: Use `maxAgeHours` instead for more precise control over content freshness.\n\nOptions for livecrawling pages.\n'never': Disable livecrawling (default for neural search).\n'fallback': Livecrawl when cache is empty.\n'preferred': Always try to livecrawl, but fall back to cache if crawling fails.\n'always': Always live-crawl, never use cache. Only use if you cannot tolerate any cached content. This option is not recommended unless consulted with the Exa team.\n"
},
"highlights": {
"oneOf": [
{
"type": "boolean",
"title": "Simple highlights retrieval",
"description": "If true, returns highlights with default settings. If false, disables highlights."
},
{
"type": "object",
"title": "Advanced highlights options",
"properties": {
"query": {
"type": "string",
"example": "Key advancements",
"description": "Custom query to direct the LLM's selection of highlights."
},
"numSentences": {
"type": "integer",
"example": 1,
"minimum": 1,
"deprecated": true,
"description": "Deprecated: use maxCharacters instead. The number of sentences to return for each snippet."
},
"maxCharacters": {
"type": "integer",
"example": 2000,
"minimum": 1,
"description": "Maximum number of characters to return for highlights. Controls the total length of highlight text returned per URL."
},
"highlightsPerUrl": {
"type": "integer",
"minimum": 1,
"deprecated": true,
"description": "Deprecated: use maxCharacters instead. The number of snippets to return for each result."
}
},
"description": "Advanced options for controlling highlight extraction. Use this when you need to customize the number of sentences, highlights per URL, or provide a custom query."
}
],
"description": "Text snippets the LLM identifies as most relevant from each page."
},
"maxAgeHours": {
"type": "integer",
"example": 24,
"description": "Maximum age of cached content in hours. Controls when livecrawling is triggered based on content freshness.\n- Positive value (e.g. 24): Use cached content if it's less than this many hours old, otherwise livecrawl.\n- 0: Always livecrawl, never use cache.\n- -1: Never livecrawl, always use cache.\n- Omit (default): Livecrawl as fallback only when no cached content exists.\n"
},
"subpageTarget": {
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"type": "string"
}
}
],
"example": "sources",
"description": "Keyword to find specific subpages of search results. Can be a single string or an array of strings, comma delimited."
},
"livecrawlTimeout": {
"type": "integer",
"default": 10000,
"example": 1000,
"description": "The timeout for livecrawling in milliseconds."
}
}
}
]
},
"type": "http",
"method": "POST",
"bodyType": "json"
}Output schema
{
"type": "object",
"properties": {
"context": {
"type": "string",
"description": "Deprecated. Combined context string from search results. Use highlights or text instead."
},
"results": {
"type": "array",
"items": {
"allOf": [
{
"type": "object",
"properties": {
"id": {
"type": "string",
"example": "https://arxiv.org/abs/2307.06435",
"description": "The temporary ID for the document. Useful for /contents endpoint."
},
"url": {
"type": "string",
"format": "uri",
"example": "https://arxiv.org/pdf/2307.06435.pdf",
"description": "The URL of the search result."
},
"image": {
"type": "string",
"format": "uri",
"example": "https://arxiv.org/pdf/2307.06435.pdf/page_1.png",
"description": "The URL of an image associated with the search result, if available."
},
"score": {
"type": [
"number",
"null"
],
"example": 0.4600165784358978,
"description": "A number from 0 to 1 representing similarity between the query/url and the result."
},
"title": {
"type": "string",
"example": "A Comprehensive Overview of Large Language Models",
"description": "The title of the search result."
},
"author": {
"type": [
"string",
"null"
],
"example": "Humza Naveed, University of Engineering and Technology (UET), Lahore, Pakistan",
"description": "If available, the author of the content."
},
"favicon": {
"type": "string",
"format": "uri",
"example": "https://arxiv.org/favicon.ico",
"description": "The URL of the favicon for the search result's domain."
},
"publishedDate": {
"type": [
"string",
"null"
],
"example": "2023-11-16T01:36:32.547Z",
"description": "An estimate of the creation date, from parsing HTML content. Format is YYYY-MM-DD."
}
}
},
{
"type": "object",
"properties": {
"text": {
"type": "string",
"example": "Abstract Large Language Models (LLMs) have recently demonstrated remarkable capabilities...",
"description": "The full content text of the search result."
},
"extras": {
"type": "object",
"properties": {
"links": {
"type": "array",
"items": {
"type": "string"
},
"example": [],
"description": "Array of links from the search result."
}
},
"description": "Results from extras."
},
"summary": {
"type": "string",
"example": "This overview paper on Large Language Models (LLMs) highlights key developments...",
"description": "Summary of the webpage"
},
"entities": {
"type": "array",
"items": {
"oneOf": [
{
"type": "object",
"required": [
"id",
"type",
"version",
"properties"
],
"properties": {
"id": {
"type": "string",
"example": "https://exa.ai/library/company/exa",
"description": "Exa entity ID."
},
"type": {
"enum": [
"company"
],
"type": "string",
"example": "company",
"description": "Entity type discriminator."
},
"version": {
"type": "integer",
"example": 1,
"description": "Schema version number."
},
"properties": {
"type": "object",
"properties": {
"name": {
"type": [
"string",
"null"
],
"example": "Exa",
"description": "Company name."
},
"workforce": {
"oneOf": [
{
"type": "object",
"properties": {
"total": {
"type": [
"integer",
"null"
],
"example": 500,
"description": "Total number of employees."
}
},
"description": "Company workforce information."
},
{
"type": "null"
}
]
},
"financials": {
"oneOf": [
{
"type": "object",
"properties": {
"fundingTotal": {
"type": [
"integer",
"null"
],
"example": 500000000,
"description": "Total funding raised in USD."
},
"revenueAnnual": {
"type": [
"integer",
"null"
],
"example": 1000000000,
"description": "Annual revenue in USD."
},
"fundingLatestRound": {
"oneOf": [
{
"type": "object",
"properties": {
"date": {
"type": [
"string",
"null"
],
"example": "2023-06-15",
"description": "Date of the funding round."
},
"name": {
"type": [
"string",
"null"
],
"example": "Series B",
"description": "Name of the funding round (e.g., \"Series A\", \"Seed\")."
},
"amount": {
"type": [
"integer",
"null"
],
"example": 50000000,
"description": "Amount raised in USD."
}
},
"description": "Funding round information."
},
{
"type": "null"
}
]
}
},
"description": "Company financial information."
},
{
"type": "null"
}
]
},
"webTraffic": {
"oneOf": [
{
"type": "object",
"properties": {
"visitsMonthly": {
"type": [
"integer",
"null"
],
"example": 266306714,
"description": "Estimated monthly website visits."
}
},
"description": "Company web traffic information."
},
{
"type": "null"
}
]
},
"description": {
"type": [
"string",
"null"
],
"example": "AI-powered search engine",
"description": "Brief description of the company."
},
"foundedYear": {
"type": [
"integer",
"null"
],
"example": 2022,
"description": "Year the company was founded."
},
"headquarters": {
"oneOf": [
{
"type": "object",
"properties": {
"city": {
"type": [
"string",
"null"
],
"example": "San Francisco",
"description": "City name."
},
"address": {
"type": [
"string",
"null"
],
"example": "123 Main St",
"description": "Street address."
},
"country": {
"type": [
"string",
"null"
],
"example": "United States",
"description": "Full country name."
},
"postalCode": {
"type": [
"string",
"null"
],
"example": "94105",
"description": "Postal/ZIP code."
}
},
"description": "Company headquarters information."
},
{
"type": "null"
}
]
}
},
"description": "Structured properties for a company entity."
}
},
"description": "Structured entity data for a company."
},
{
"type": "object",
"required": [
"id",
"type",
"version",
"properties"
],
"properties": {
"id": {
"type": "string",
"example": "https://exa.ai/library/person/john-doe",
"description": "Exa entity ID."
},
"type": {
"enum": [
"person"
],
"type": "string",
"example": "person",
"description": "Entity type discriminator."
},
"version": {
"type": "integer",
"example": 1,
"description": "Schema version number."
},
"properties": {
"type": "object",
"properties": {
"name": {
"type": [
"string",
"null"
],
"example": "John Doe",
"description": "Person's full name."
},
"location": {
"type": [
"string",
"null"
],
"example": "San Francisco, CA",
"description": "Person's location."
},
"workHistory": {
"type": "array",
"items": {
"type": "object",
"properties": {
"dates": {
"oneOf": [
{
"type": "object",
"properties": {
"to": {
"type": [
"string",
"null"
],
"example": "2023-06-30",
"description": "End date (YYYY-MM-DD format)."
},
"from": {
"type": [
"string",
"null"
],
"example": "2020-01-15",
"description": "Start date (YYYY-MM-DD format)."
}
},
"description": "Date range for work history entries."
},
{
"type": "null"
}
]
},
"title": {
"type": [
"string",
"null"
],
"example": "Software Engineer",
"description": "Job title."
},
"company": {
"oneOf": [
{
"type": "object",
"properties": {
"id": {
"type": [
"string",
"null"
],
"example": "https://exa.ai/library/company/exa",
"description": "Exa entity ID for the company."
},
"name": {
"type": [
"string",
"null"
],
"example": "Exa",
"description": "Company name."
}
},
"description": "Reference to a company in work history."
},
{
"type": "null"
}
]
},
"location": {
"type": [
"string",
"null"
],
"example": "San Francisco, CA",
"description": "Work location."
}
},
"description": "A single work history entry for a person."
},
"description": "List of work history entries."
}
},
"description": "Structured properties for a person entity."
}
},
"description": "Structured entity data for a person."
}
],
"description": "Structured entity data for company or person search results. Only returned for category=company or category=people searches.",
"discriminator": {
"mapping": {
"person": "#/components/schemas/PersonEntity",
"company": "#/components/schemas/CompanyEntity"
},
"propertyName": "type"
}
},
"description": "Structured entity data for company or person search results. Only returned for category=company or category=people searches."
},
"subpages": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ResultWithContent"
},
"example": [
{
"id": "https://arxiv.org/abs/2303.17580",
"url": "https://arxiv.org/pdf/2303.17580.pdf",
"text": "HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face Date Published: 2023-05-25 Authors: Yongliang Shen, Microsoft Research Asia Kaitao Song, Microsoft Research Asia Xu Tan, Microsoft Research Asia Dongsheng Li, Microsoft Research Asia Weiming Lu, Microsoft Research Asia Yueting Zhuang, Microsoft Research Asia, yzhuang@zju.edu.cn Zhejiang University, Microsoft Research Asia Microsoft Research, Microsoft Research Asia Abstract Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence. While there are abundant AI models available for different domains and modalities, they cannot handle complicated AI tasks. Considering large language models (LLMs) have exhibited exceptional ability in language understanding, generation, interaction, and reasoning, we advocate that LLMs could act as a controller to manage existing AI models to solve complicated AI tasks and language could be a generic interface to empower t",
"title": "HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face",
"author": "Yongliang Shen, Microsoft Research Asia, Kaitao Song, Microsoft Research Asia, Xu Tan, Microsoft Research Asia, Dongsheng Li, Microsoft Research Asia, Weiming Lu, Microsoft Research Asia, Yueting Zhuang, Microsoft Research Asia, yzhuang@zju.edu.cn, Zhejiang University, Microsoft Research Asia, Microsoft Research, Microsoft Research Asia",
"summary": "HuggingGPT is a framework using ChatGPT as a central controller to orchestrate various AI models from Hugging Face to solve complex tasks. ChatGPT plans the task, selects appropriate models based on their descriptions, executes subtasks, and summarizes the results. This approach addresses limitations of LLMs by allowing them to handle multimodal data (vision, speech) and coordinate multiple models for complex tasks, paving the way for more advanced AI systems.",
"highlights": [
"2) Recently, some researchers started to investigate the integration of using tools or models in LLMs ."
],
"publishedDate": "2023-11-16T01:36:20.486Z",
"highlightScores": [
0.32679107785224915
]
}
],
"description": "Array of subpages for the search result."
},
"highlights": {
"type": "array",
"items": {
"type": "string"
},
"example": [
"Such requirements have limited their adoption..."
],
"description": "Array of highlights extracted from the search result content."
},
"highlightScores": {
"type": "array",
"items": {
"type": "number",
"format": "float"
},
"example": [
0.4600165784358978
],
"description": "Array of cosine similarity scores for each highlighted"
}
}
}
]
}
},
"statuses": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"example": "https://example.com",
"description": "The URL that was requested"
},
"error": {
"type": "object",
"nullable": true,
"properties": {
"tag": {
"enum": [
"CRAWL_NOT_FOUND",
"CRAWL_TIMEOUT",
"CRAWL_LIVECRAWL_TIMEOUT",
"SOURCE_NOT_AVAILABLE",
"UNSUPPORTED_URL",
"CRAWL_UNKNOWN_ERROR"
],
"type": "string",
"example": "CRAWL_NOT_FOUND",
"description": "Specific error type"
},
"httpStatusCode": {
"type": "integer",
"example": 404,
"nullable": true,
"description": "The corresponding HTTP status code"
}
},
"description": "Error details, only present when status is \"error\""
},
"status": {
"enum": [
"success",
"error"
],
"type": "string",
"example": "success",
"description": "Status of the content fetch operation"
}
}
},
"description": "Status information for each requested URL"
},
"requestId": {
"type": "string",
"example": "e492118ccdedcba5088bfc4357a8a125",
"description": "Unique identifier for the request"
},
"costDollars": {
"type": "object",
"properties": {
"total": {
"type": "number",
"format": "float",
"example": 0.005,
"description": "Total dollar cost for your request"
},
"breakDown": {
"type": "array",
"items": {
"type": "object",
"properties": {
"search": {
"type": "number",
"format": "float",
"example": 0.005,
"description": "Cost of your search operations"
},
"contents": {
"type": "number",
"format": "float",
"example": 0,
"description": "Cost of your content operations"
},
"breakdown": {
"type": "object",
"properties": {
"deepSearch": {
"type": "number",
"format": "float",
"example": 0.015,
"description": "Cost of your deep search operations"
},
"contentText": {
"type": "number",
"format": "float",
"example": 0,
"description": "Cost of your text content retrieval"
},
"neuralSearch": {
"type": "number",
"format": "float",
"example": 0.005,
"description": "Cost of your neural search operations"
},
"contentSummary": {
"type": "number",
"format": "float",
"example": 0,
"description": "Cost of your summary generation"
},
"contentHighlight": {
"type": "number",
"format": "float",
"example": 0,
"description": "Cost of your highlight generation"
}
}
}
}
},
"description": "Breakdown of costs by operation type"
},
"perPagePrices": {
"type": "object",
"properties": {
"contentText": {
"type": "number",
"format": "float",
"example": 0.001,
"description": "Standard price per page for text content"
},
"contentSummary": {
"type": "number",
"format": "float",
"example": 0.001,
"description": "Standard price per page for summaries"
},
"contentHighlight": {
"type": "number",
"format": "float",
"example": 0.001,
"description": "Standard price per page for highlights"
}
},
"description": "Standard price per page for different content operations"
},
"perRequestPrices": {
"type": "object",
"properties": {
"deepSearch_1_25_results": {
"type": "number",
"format": "float",
"example": 0.015,
"description": "Standard price for deep search with 1-25 results"
},
"deepSearch_26_100_results": {
"type": "number",
"format": "float",
"example": 0.075,
"description": "Standard price for deep search with 26-100 results"
},
"neuralSearch_1_25_results": {
"type": "number",
"format": "float",
"example": 0.005,
"description": "Standard price for neural search with 1-25 results"
},
"neuralSearch_26_100_results": {
"type": "number",
"format": "float",
"example": 0.025,
"description": "Standard price for neural search with 26-100 results"
},
"neuralSearch_100_plus_results": {
"type": "number",
"format": "float",
"example": 1,
"description": "Standard price for neural search with 100+ results"
}
},
"description": "Standard price per request for different operations"
}
}
}
}
}