# Serper Google Scholar - Core.Today AI API

> Google Scholar results through Serper - paper title, authors and venue, snippet, year, citation count and PDF link. 3 credits per search.

- **Provider**: Serper
- **Model ID**: serper/scholar
- **Category**: Web Search
- **Credits**: 3 per search
- **Speed**: Fast
- **Quality**: High

## Features
- Academic papers with citation counts
- PDF links when available
- Publication info and year

## Use Cases
- Literature review agents
- Citation lookups
- Research trend tracking

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **q**: string - The search query.

### Optional
- **gl**: string - Country of the results as a lowercase ISO 3166-1 code (e.g. kr, us). Serper default us.
- **hl**: string - Language of the results (e.g. ko, en). Serper default en.
- **page**: integer (default: 1) - Results page (1 = first).

## Examples

### Basic request
A typical request with the most common options.
```json
{
  "model": "serper/scholar",
  "input": {
    "q": "retrieval augmented generation"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- The result is the provider's JSON as-is (organic)
- Links in the result point to the original pages - nothing is copied to your storage
- Billed on the credits Serper reports in the response (`credits`) - the reservation is refunded down to it

## Documentation
https://serper.dev