# Core.Today AI API — Web Search (Tavily, Serper, Brave)

> Web search, LLM grounding context and page extraction APIs (Tavily Search/Extract, Serper Google SERP and scrape, Brave LLM Context and Web Search) available through the Core.Today unified API. Results are the provider's JSON; Tavily and Serper settle on the usage the provider reports.

Source: https://console.core.today/docs/web-search
This file: https://console.core.today/llms/web-search.txt
All models: https://console.core.today/llms.txt

## API Usage

Base URL: https://api.core.today/v1
Auth header: X-API-Key: YOUR_API_KEY

1. POST /predictions with {"model": "<model id>", "input": {...}} -> returns job_id
2. GET /predictions/{job_id} -> poll until status is "completed" or "failed"
3. result contains output URL(s); add "is_public": true for a permanent public URL

## Models (12)

### Tavily Extract — `tavily/extract`

Extract clean, LLM-ready content (markdown or text) from up to 20 web pages in one call, optionally reranked to a query. Billed per successfully extracted URL - about 4 credits per URL (basic), failed URLs are refunded.

- Provider: Tavily
- Credits: 4 (per extracted URL (3.72/URL basic, 7.44 advanced; failed URLs refunded))
- Speed: fast / Quality: high
- Required params: urls (array)
- Optional params: query, chunks_per_source, extract_depth=basic, format=markdown, include_images=false, include_favicon=false, timeout
- Example input:
```json
{
  "model": "tavily/extract",
  "input": {
    "urls": [
      "https://docs.tavily.com/documentation/api-credits"
    ],
    "extract_depth": "basic",
    "format": "markdown"
  }
}
```
- Full docs: https://console.core.today/docs/models/tavily/extract

### Serper Google Images — `serper/images`

Google Images results through Serper - image URL, thumbnail, size, source page and title. 3 credits per search.

- Provider: Serper
- Credits: 3 (per search (num > 10 reserved at 5, settled on Serper's charge))
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: gl, hl, location, num=10, page=1, tbs, autocorrect=true
- Example input:
```json
{
  "model": "serper/images",
  "input": {
    "q": "seoul skyline night",
    "num": 10
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/images

### Brave LLM Context — `brave/llm-context`

Web search for AI agents from Brave's independent index - returns pre-extracted, relevance-ranked snippets per source, sized to a token budget, ready to drop into an LLM prompt. 12 credits per request.

- Provider: Brave
- Credits: 12 (per request)
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: country=US, search_lang=en, count, maximum_number_of_urls, maximum_number_of_tokens, maximum_number_of_snippets, maximum_number_of_tokens_per_url, maximum_number_of_snippets_per_url, context_threshold_mode, freshness, safesearch, spellcheck=true, goggles, enable_source_metadata=false
- Example input:
```json
{
  "model": "brave/llm-context",
  "input": {
    "q": "latest AI video generation models",
    "country": "US",
    "search_lang": "en",
    "maximum_number_of_tokens": 4096
  }
}
```
- Full docs: https://console.core.today/docs/models/brave/llm-context

### Serper Google News — `serper/news`

Google News results through Serper - headline, source, date, snippet and image for each article. 3 credits per search.

- Provider: Serper
- Credits: 3 (per search (num > 10 reserved at 5, settled on Serper's charge))
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: gl, hl, location, num=10, page=1, tbs, autocorrect=true
- Example input:
```json
{
  "model": "serper/news",
  "input": {
    "q": "생성형 AI",
    "gl": "kr",
    "hl": "ko",
    "tbs": "qdr:d"
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/news

### Serper Google Places — `serper/places`

Google Maps places through Serper - name, address, rating, review count, category, phone and coordinates. 3 credits per search.

- Provider: Serper
- Credits: 3 (per search)
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: gl, hl, location, page=1
- Example input:
```json
{
  "model": "serper/places",
  "input": {
    "q": "카페 성수동",
    "gl": "kr",
    "hl": "ko"
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/places

### Serper Google Scholar — `serper/scholar`

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

- Provider: Serper
- Credits: 3 (per search)
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: gl, hl, page=1
- Example input:
```json
{
  "model": "serper/scholar",
  "input": {
    "q": "retrieval augmented generation"
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/scholar

### Serper Scrape — `serper/scrape`

Fetch one web page through Serper - clean text (optionally markdown), page metadata and JSON-LD. 5 credits per page.

- Provider: Serper
- Credits: 5 (per page (2 Serper credits))
- Speed: fast / Quality: high
- Required params: url (string)
- Optional params: includeMarkdown=false
- Example input:
```json
{
  "model": "serper/scrape",
  "input": {
    "url": "https://docs.tavily.com/documentation/api-credits",
    "includeMarkdown": true
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/scrape

### Serper Google Search — `serper/search`

Google web search results through Serper - organic results, knowledge graph, answer box, People Also Ask and related searches. 3 credits per search.

- Provider: Serper
- Credits: 3 (per search (num > 10 reserved at 5, settled on Serper's charge))
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: gl, hl, location, num=10, page=1, tbs, autocorrect=true
- Example input:
```json
{
  "model": "serper/search",
  "input": {
    "q": "AI video generation API",
    "gl": "kr",
    "hl": "ko",
    "num": 10
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/search

### Tavily Search — `tavily/search`

Real-time web search built for LLMs and agents - returns ranked results with relevant content snippets, an optional LLM-generated answer, raw page content, images and domain/date filters. 19 credits per basic search, 38 per advanced search.

- Provider: Tavily
- Credits: 19 (per search (basic/fast/ultra-fast; 38 for advanced))
- Speed: fast / Quality: high
- Required params: query (string)
- Optional params: search_depth=basic, topic=general, max_results, chunks_per_source, time_range, start_date, end_date, include_answer, include_raw_content, include_images=false, include_image_descriptions=false, include_favicon=false, include_published_date=false, include_domains, exclude_domains, country, language, auto_parameters=false, exact_match=false, safe_search=false
- Example input:
```json
{
  "model": "tavily/search",
  "input": {
    "query": "latest AI video generation models 2026",
    "search_depth": "basic",
    "max_results": 5,
    "include_answer": "basic"
  }
}
```
- Full docs: https://console.core.today/docs/models/tavily/search

### Serper Google Shopping — `serper/shopping`

Google Shopping results through Serper - product title, price, seller, rating and image. 5 credits per search.

- Provider: Serper
- Credits: 5 (per search (2 Serper credits))
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: gl, hl, location, num=10, page=1
- Example input:
```json
{
  "model": "serper/shopping",
  "input": {
    "q": "wireless earbuds",
    "gl": "kr",
    "hl": "ko",
    "num": 20
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/shopping

### Serper Google Videos — `serper/videos`

Google Videos results through Serper - title, link, channel, duration, date and thumbnail. 3 credits per search.

- Provider: Serper
- Credits: 3 (per search (num > 10 reserved at 5, settled on Serper's charge))
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: gl, hl, location, num=10, page=1, tbs, autocorrect=true
- Example input:
```json
{
  "model": "serper/videos",
  "input": {
    "q": "Seedance 2.5 tutorial",
    "num": 10
  }
}
```
- Full docs: https://console.core.today/docs/models/serper/videos

### Brave Web Search — `brave/web-search`

Search results pages from Brave's independent index - web results plus news, videos, discussions, FAQ and infobox clusters, with country, language, freshness and Goggles controls. 12 credits per request.

- Provider: Brave
- Credits: 12 (per request)
- Speed: fast / Quality: high
- Required params: q (string)
- Optional params: country=US, search_lang=en, ui_lang, count=20, offset=0, safesearch=moderate, freshness, result_filter, extra_snippets=false, spellcheck=true, text_decorations=true, units, goggles, operators=true
- Example input:
```json
{
  "model": "brave/web-search",
  "input": {
    "q": "생성형 AI API 비교",
    "country": "KR",
    "search_lang": "ko",
    "count": 10
  }
}
```
- Full docs: https://console.core.today/docs/models/brave/web-search