Tavily-Search
Tavily-Search
Provider: Tavily
Category: Research & Search
Endpoint: POST /v1/search
Context window: —
Served from: —
Web search with crawl, extract, and URL mapping for fast, structured retrieval across pages and domains for downstream pipelines.
At a glance
| Field | Value |
|---|---|
| Model id | tavily-search-test |
| Input modalities | text |
| Output modalities | text |
| Context window | — |
| Region | — |
| Features | web_search, crawl, extract, map |
| New | No |
| Native inference | No |
Pricing
| Charge | Spec | Rate |
|---|---|---|
| Search (Basic/Fast/Ultra-Fast) | per search | $0.0096 |
| Search (Advanced) | per search | $0.019 |
| Search (Advanced + Answer) | per search | $0.029 |
| Extract (Basic) | per 5 URLs | $0.0096 |
| Extract (Advanced) | per 5 URLs | $0.019 |
| Crawl/Map (basic) | per 10 pages | $0.0096 |
Example request
$ curl https://api.empiriolabs.ai/v1/search \ > -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \ > -H 'Content-Type: application/json' \ > -d '{"model": "tavily-search-test", "query": "latest LLM benchmarks 2026"}'
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
query | string | yes | — | Search query / URL / sitemap target depending on operation_mode. |
operation_mode | enum | no | "Search" | Search: query the web. Crawl: spider a site. Extract: pull structured fields from one URL. Map: list URLs on a site. · Allowed: Search, Crawl, Extract, Map |
search_depth | enum | no | "basic" | basic: cheapest. advanced: more sources. fast: latency-optimized. ultra-fast: minimum latency. · Allowed: basic, advanced, fast, ultra-fast |
topic | enum | no | "general" | general: any source. news: news only. finance: financial sources only. · Allowed: general, news, finance |
max_results | number | no | 5 | Sources to return. · Range: 1 – 20 |
search_chunks_per_source | number | no | 3 | Advanced depth only. Snippet count per source. · Range: 1 – 3 |
include_answer | enum | no | "false" | false: no LLM-summarized answer. basic: short. advanced: longer with citations. · Allowed: false, basic, advanced |
include_raw_content | enum | no | "false" | Return cleaned page contents. · Allowed: false, markdown, text |
include_images | boolean | no | false | Include image URLs. |
include_image_descriptions | boolean | no | false | Add captions to image URLs. |
include_favicon | boolean | no | false | Include favicon URLs. |
auto_parameters | boolean | no | false | Let Tavily auto-tune depth/topic/etc based on the query. |
include_domains | string | no | — | Comma-separated allowlist. |
exclude_domains | string | no | — | Comma-separated denylist. |
time_range | enum | no | — | Restrict to results from the last N. · Allowed: none, day, week, month, year |
start_date | string | no | — | YYYY-MM-DD lower bound for publication date. |
end_date | string | no | — | YYYY-MM-DD upper bound for publication date. |
days | number | no | — | News topic only. Recency window in days. · Range: 1 – 365 |
country | string | no | — | ISO alpha-2 country bias (general topic only). |
crawl_limit | number | no | 50 | Crawl mode. Total page cap. · Range: 1 – 100 |
crawl_max_depth | number | no | 1 | Crawl mode. Max click depth. · Range: 1 – 5 |
crawl_max_breadth | number | no | 20 | Crawl mode. Max links per page. · Range: 1 – 50 |
crawl_extract_depth | enum | no | "basic" | Crawl mode. basic: cleaned text. advanced: structured fields. · Allowed: basic, advanced |
crawl_format | enum | no | "markdown" | Crawl mode. Output format. · Allowed: markdown, text |
crawl_instructions | string | no | — | Crawl mode. Free-form crawl instructions. |
crawl_select_paths | string | no | — | Crawl mode. Comma-separated path patterns to include. |
crawl_exclude_paths | string | no | — | Crawl mode. Comma-separated path patterns to skip. |
crawl_timeout | number | no | 30 | Crawl mode. Per-page fetch timeout in seconds. · Range: 10 – 150 |
extract_depth | enum | no | "basic" | Extract mode. basic: cleaned text. advanced: structured fields. · Allowed: basic, advanced |
extract_format | enum | no | "markdown" | Extract mode. Output format. · Allowed: markdown, text |
extract_query | string | no | — | Extract mode. Question/instruction to extract specific fields. |
disable_formatting | boolean | no | false | Return raw upstream response. |
Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/tavily-search-test.
