OriginRouter Platform
API ResourcesWeb

Web

The Web API provides a variety of web-related AI capabilities, including common functions such as web search.

With an OriginRouter One subscription, choose the corresponding Coding API endpoint and make sure the model ID comes from the Supported Models list; with the pay-as-you-go API plan, choose the corresponding Beta API endpoint and make sure the model ID comes from the Model List; a plan and endpoint mismatch may make models unavailable or result in unexpected billing.

POST/beta/v1/web/search

The Web Search API is a powerful set of interface tools designed to connect your application with the real-time Internet. It can efficiently fetch the content of specified web page links and parse them from complex HTML format into clean, structured text or data.

Request Headers

  • Name
    Content-Type
    Type
    string
    Required
    Required
    Description
    Value must be application/json.
  • Name
    Authorization
    Type
    string
    Optional
    Optional
    Description
    Optional authentication method. The credential used for API authentication. For details, see Authentication.
  • Name
    x-api-key
    Type
    string
    Optional
    Optional
    Description
    Optional authentication method. Pass your API key directly. Note: Do not use both Authorization and x-api-key simultaneously.

Request Body

  • Name
    model
    Type
    string
    Required
    Required
    Description
    The model ID to use. Currently available web search models include web-search-lite and web-search-base.
  • Name
    topic
    Type
    string
    Required
    Required
    Description
    The keywords or topic you want to search for on the web. The system will crawl and analyze relevant web pages around this topic.

Response Body

  • Name
    id
    Type
    string
    Required
    Required
    Description
    The unique identifier for this fetch request.
  • Name
    text
    Type
    string
    Required
    Required
    Description
    Comprehensive answers or summaries generated by the model based on real-time web search results. The text may contain citation markers like [1] or [1, 2, 10], which correspond to the source information in the citations field, indicating the source of the content.
  • Name
    urls
    Type
    array
    Required
    Required
    Description
    A string array that lists all original web links referenced and cited during the answer generation process.
  • Name
    citations
    Type
    array
    Required
    Required
    Description
    An array of objects providing detailed information for each citation source in the answer, used for content verification and source tracing.

Request

POST
/beta/v1/web/search
curl --location 'https://api.easytransnote.com/beta/v1/web/search' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "web-search-base",
    "topic": "latest AI technology developments"
  }'

Response

{
    "text": "Based on my web search results...\n\n**International News:**\n\n* **India and Shanghai Cooperation Organization (SCO):** India refused to sign the SCO joint declaration...[1, 2, 10]\n* **US and Iran:** President Trump threatened to sue the New York Times and CNN...[7]...",
    "urls": [
        "https://news24online.com/education/school-assembly-news-headlines-today-top-international-sports-and-national-news-for-june-27/594903/",
        "https://www.jagranjosh.com/articles/school-assembly-news-headlines-today-27-june-2025-govt-authorises-aadhaar-authentication-for-ibps-exams-to-curb-impersonation-union-minister-gadkari-dismisses-reports-on-twowheeler-toll-tax-and-other-news-1800000424-1",
        "https://timesofindia.indiatimes.com/business/india-business/top-stock-recommendations-for-june-27-2025-tata-steel-lloyds-engineering-works-stocks-to-buy-today/articleshow/122090714.cms",
        "..."
    ],
    "citations": [
        {
            "start_index": 868,
            "end_index": 1022,
            "segments": [
                {
                    "label": "wikipedia",
                    "short_url": "https://easytransnote.com/id/1f9c...ba0-8",
                    "value": "https://en.wikipedia.org/wiki/Portal:Current_events/June_2025"
                }
            ]
        },
        {
            "start_index": 1023,
            "end_index": 1221,
            "segments": [
                {
                    "label": "wikipedia",
                    "short_url": "https://easytransnote.com/id/1f9c...ba0-8",
                    "value": "https://en.wikipedia.org/wiki/Portal:Current_events/June_2025"
                }
            ]
        }
        // ... more citation objects
    ]
}
POST/beta/v1/web/fetch

Web Fetch

The Web Fetch API can efficiently fetch the content of a specified web page URL and parse it from complex HTML format into clean Markdown text and raw HTML.

Request Headers

  • Name
    Content-Type
    Type
    string
    Required
    Required
    Description
    Value must be application/json.
  • Name
    Authorization
    Type
    string
    Optional
    Optional
    Description
    Optional authentication method. The credential used for API authentication. For details, see Authentication.
  • Name
    x-api-key
    Type
    string
    Optional
    Optional
    Description
    Optional authentication method. Pass your API key directly. Note: Do not use both Authorization and x-api-key simultaneously.

Request Body

  • Name
    model
    Type
    string
    Required
    Required
    Description
    The model ID to use. Currently available web fetch models include web-fetch-lite.
  • Name
    url
    Type
    string
    Required
    Required
    Description
    The target web page URL to fetch. The system will retrieve the page and parse its content.

Response Body

  • Name
    id
    Type
    string
    Required
    Required
    Description
    The unique identifier for this fetch request.
  • Name
    markdown
    Type
    string
    Required
    Required
    Description
    The Markdown format text of the target web page content after parsing.
  • Name
    html
    Type
    string
    Required
    Required
    Description
    The raw HTML content of the target web page.

Request

POST
/beta/v1/web/fetch
curl --location 'https://api.easytransnote.com/beta/v1/web/fetch' \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "web-fetch-lite",
    "url": "https://en.wikipedia.org/wiki/Artificial_intelligence"
  }'

Response

{
    "id": "web_a1b2c3d4e5f6",
    "markdown": "# Artificial intelligence\n\nArtificial intelligence (AI) is the intelligence of machines or software...",
    "html": "<html><head>...</head><body>...</body></html>"
}

Was this page helpful?