← Back to Linkup
POST/research

Research

Creates an asynchronous research task that performs comprehensive multi-step web research. Returns a task ID immediately. Poll GET /research/:id for results.

Linkup·Dynamic pricing

Dynamic pricing

body.reasoningDepth == "S" ? 0.25 : body.reasoningDepth == "M" ? 0.50 : body.reasoningDepth == "XL" ? 2.50 : 1.50

Example code

// Using @orth/sdk - The simplest way to call APIs // Install: npm install @orth/sdk import Orthogonal from "@orth/sdk"; const orthogonal = new Orthogonal({ apiKey: process.env.ORTHOGONAL_API_KEY, }); const output = await orthogonal.run({ api: "linkup", path: "/research", body: { "q": "example", "outputType": "example" } }); console.log(output);

Body parameters

qrequired
string

The natural language question for which you want to perform research.

outputTyperequired
string

The type of output. Use sourcedAnswer for a sourced text answer, or structured for a custom-formatted response defined by structuredOutputSchema.

reasoningDepth
string

Pin the reasoning depth (S < M < L < XL). Defaults to L. Higher depths trade latency for thoroughness.

mode
string

Pin the research agent mode: answer, investigate, research, or auto (default). Omit to let the agent auto-classify.

structuredOutputSchema
object

Required only when outputType is structured. JSON schema representing the desired response format. Root must be type object.

fromDate
string

Start date for results in ISO 8601 format (YYYY-MM-DD).

toDate
string

End date for results in ISO 8601 format (YYYY-MM-DD).

includeDomains
string

Domains to restrict search to. Up to 100 domains.

excludeDomains
string

Domains to exclude from search.

Response

id
string

Unique identifier of the research task.

status
string

Current status: pending, processing, completed, or failed.

createdAt
string

ISO 8601 timestamp when the task was created.

updatedAt
string

ISO 8601 timestamp when the task was last updated.

error
string

Error message if the task failed. Null otherwise.

    Orthogonal - Giving AI agents the tools they need.