Web search with crawl, extract, and URL mapping for fast, structured retrieval across pages and domains for downstream pipelines.
TavilyResearch & SearchProprietary EndpointWeb search with crawl, extract, and URL mapping for fast, structured retrieval across pages and domains for downstream pipelines.
tavily-searchPOST /v1/searchLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
Tavily Search answers live queries through POST /v1/search. Send the search query with the model id tavily-search and read structured results from the response. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/search \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tavily-search",
"query": "latest developments in solid-state batteries"
}'import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/search",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "tavily-search",
"query": "latest developments in solid-state batteries",
},
)
print(response.json())Request parameters supported by the Tavily Search API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| query | string | - | - | The natural-language search query. |
| operation_mode | enum | Search | Search, Crawl, Extract, Map | search | extract | crawl | map. Determines which Tavily endpoint runs. |
| search_depth | enum | basic | basic, advanced | basic = fast and cheap, advanced = deeper crawl per result with full content. |
| search_chunks_per_source | number | 3 | 1 to 3 | Number of relevant content chunks to extract per source. |
| search_topic | enum | general | general, news, finance | Search topic preset (general, news, finance, etc.). Alias of topic. |
| include_answer | boolean | true | - | basic | advanced | false. Returns a synthesized answer alongside the results. |
| include_raw_content | boolean | false | - | Include the raw HTML content alongside cleaned text. |
| include_images | boolean | false | - | Include image URLs from the search results. |
| include_image_descriptions | boolean | false | - | Include AI-generated descriptions of returned images. |
| include_favicon | boolean | false | - | Include the favicon URL of each source. |
| auto_parameters | boolean | false | - | Let Tavily auto-pick search_depth and other knobs based on the query. |
| max_results | number | 5 | 1 to 20 | Maximum number of results to return (1-50). |
| time_range | enum | - | day, week, month, year | day | week | month | year. Restrict results to this recency window. |
| start_date | string | - | - | Only include sources published after this date (YYYY-MM-DD). |
On EmpirioLabs, Tavily Search is billed pay as you go: Search (Basic/Fast/Ultra-Fast) $0.0096 per search; Search (Advanced) $0.019 per search; Search (Advanced + Answer) $0.029 per search. The live rate card on this page always matches what the API charges.
Tavily Search is served through POST /v1/search on api.empiriolabs.ai with standard bearer-token authentication.
Yes. The EmpirioLabs playground runs Tavily Search in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Explore our models, or contact us about business inquiries, custom deployments, or anything else.
