OpenAI SDK

Documentation Index

Fetch the complete documentation index at: https://docs.linkup.so/llms.txt

Use this file to discover all available pages before exploring further.

​

Introduction

​

Quickstart

pip install openai

from openai import OpenAI

client = OpenAI(
  base_url='https://api.linkup.so/v1',
  api_key="<YOUR API KEY>"
)

response = client.responses.create(
  model="linkup-standard",
  input="Can you tell me which women were awarded the Physics Nobel Prize",
)

print(response.output_text)

npm i openai

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.linkup.so/v1',
  apiKey: "<YOUR API KEY>"
});

const response = await client.responses.create({
  model: "linkup-standard",
  input: "Can you tell me which women were awarded the Physics Nobel Prize",
});

console.log(response.output_text);

​

Input parameters

​

Model

• "linkup-fast" (beta): the fastest mode. A single-pass, keyword-like search with no LLM involvement for query interpretation, reformulation, or evaluation. Optimized for conversational use cases where low latency is key (e.g. “weather in Paris today”)
• "linkup-standard": the search will leverage agentic search for a fast yet accurate result, suited for queries that do not rely on sequential steps being performed or several pages being scraped (e.g. “What’s the weather in Paris today?”)
• "linkup-deep": the search will use a full agentic workflow with up to 10 iterations to solve more complex queries (e.g. “First, find Linkup website domain. Then scrape the homepage, product page, and about us page. Then search for recent news. Consolidate the output in a comprehensive company profile”). Runs longer than the other depths.

​

Using structured output (advanced)

pip install openai pydantic

from openai import OpenAI
from pydantic import BaseModel

class Winner(BaseModel):
  name: str
  year: str

class Response(BaseModel):
  winners: list[Winner]

client = OpenAI(
  base_url='https://api.linkup.so/v1',
  api_key="<YOUR API KEY>"
)

response = client.responses.parse(
  model="linkup-standard",
  input="Can you tell me which women were awarded the Physics Nobel Prize",
  text_format=Response,
)

print(response.output_parsed)

npm i openai zod

import OpenAI from 'openai';
import { zodTextFormat } from 'openai/helpers/zod.mjs';
import { z } from "zod";

const client = new OpenAI({
  baseURL: 'https://api.linkup.so/v1',
  apiKey: "<YOUR API KEY>"
});

const NobelWinners = z.object({
  winners: z.array(
    z.object({
      name: z.string(),
      year: z.string(),
    })
  )
});

const response = await client.responses.create({
  model: "linkup-standard",
  input: "Can you tell me which women were awarded the Physics Nobel Prize",
  text: {
    format: zodTextFormat(NobelWinners, "winners"),
  }
});

console.log(response.output_text);