Fetch structured output - Linkup API Documentation

Fetch can now return typed JSON from a known URL on the same /fetch call. Pass a JSON Schema in schema and the response keeps the existing markdown while adding data. Optional instructions steer extraction for rules the schema cannot express. Default Fetch is unchanged: URL in, markdown out.

What’s new

schema — JSON Schema of type "object". Turns structured output on. Field descriptions tell the model what to look for.
instructions — optional. Requires schema. Maximum 4,000 characters.
data — present in the response only when schema is set. Fields with no grounded value are omitted, even if marked required.
Same call otherwise: mode, renderJs, raw content, and images are independent.

Fetch still reads this URL only. It does not follow links. For many rows from a listing page, use Extract. Search structured output stays on structuredOutputSchema.

How to use

curl -X POST "https://api.linkup.so/v1/fetch" \
  -H "Authorization: Bearer $LINKUP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.linkup.so/careers",
    "schema": {
      "type": "object",
      "properties": {
        "jobs": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "position": {
                "type": "string",
                "description": "The job title or position"
              },
              "city": {
                "type": "string",
                "description": "The city where the job is located"
              }
            }
          }
        }
      }
    },
    "instructions": "If a position is listed in multiple cities, emit one jobs item per city so jobs[].city is a single city."
  }'

from linkup import LinkupClient

client = LinkupClient(api_key="<YOUR_LINKUP_API_KEY>")

response = client.fetch(
    url="https://www.linkup.so/careers",
    schema={
        "type": "object",
        "properties": {
            "jobs": {
                "type": "array",
                "items": {
                    "type": "object",
                    "properties": {
                        "position": {
                            "type": "string",
                            "description": "The job title or position",
                        },
                        "city": {
                            "type": "string",
                            "description": "The city where the job is located",
                        },
                    },
                },
            }
        },
    },
    instructions="If a position is listed in multiple cities, emit one jobs item per city so jobs[].city is a single city.",
)
print(response.data)

import { LinkupClient } from 'linkup-sdk';

const client = new LinkupClient({ apiKey: '<YOUR_LINKUP_API_KEY>' });

const response = await client.fetch({
  url: 'https://www.linkup.so/careers',
  schema: {
    type: 'object',
    properties: {
      jobs: {
        type: 'array',
        items: {
          type: 'object',
          properties: {
            position: {
              type: 'string',
              description: 'The job title or position',
            },
            city: {
              type: 'string',
              description: 'The city where the job is located',
            },
          },
        },
      },
    },
  },
  instructions:
    'If a position is listed in multiple cities, emit one jobs item per city so jobs[].city is a single city.',
});
console.log(response.data);

If your current SDK release does not accept schema or instructions, send the same JSON body to POST /v1/fetch.

Pricing

Adding a schema adds a flat $0.001 on top of any combination of mode and renderJs.

`mode`	`renderJs`	Markdown only	With `schema`
`"standard"`	`false`	$0.001 per call	$0.002 per call
`"standard"`	`true`	$0.005 per call	$0.006 per call
`"pro"`	`false`	$0.005 per call	$0.006 per call
`"pro"`	`true`	$0.01 per call	$0.011 per call

For schema design, missing-field behavior, and when to use Fetch versus Extract or Search, see Fetch best practices.

⌘I