Exa-Search
Exa-Search
Provider: Exa
Category: Research & Search
Endpoint: POST /v1/search
Context window: —
Served from: —
Web search engine for finding pages, retrieving similar pages, crawling, and dedicated code search across the open web for AI agents.
At a glance
| Field | Value |
|---|---|
| Model id | exa-search |
| Input modalities | text |
| Output modalities | text |
| Context window | — |
| Region | — |
| Features | web_search, semantic_search |
| New | No |
| Native inference | No |
Pricing
| Charge | Spec | Rate |
|---|---|---|
| Search (1-25 results) | per search | $0.0060 |
| Search (26-100 results) | per search | $0.030 |
| Content (Text/Highlights/Summary) | per page/feature | $0.0060 |
| Code Search | per 1k tokens | $0.0060 |
Example request
$ curl https://api.empiriolabs.ai/v1/search \ > -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \ > -H 'Content-Type: application/json' \ > -d '{"model": "exa-search", "query": "latest LLM benchmarks 2026"}'
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
query | string | yes | — | Search query, or URL for ‘similar’ operation, or repo path for ‘code’ operation. |
operation | enum | no | "search" | search: keyword/neural search. similar: pages similar to the URL in query. contents: fetch full text of given URLs. code: code-aware search. · Allowed: search, similar, contents, code |
search_type | enum | no | "auto" | auto: Exa picks. instant: cheapest, fastest. neural: semantic search. deep: thorough. fast: speed-optimized. · Allowed: auto, instant, neural, deep, fast |
num_results | number | no | 10 | Number of results to return. · Range: 1 – 100 |
category | enum | no | — | Restrict by source category. · Allowed: “, company, research paper, news, pdf, github, tweet, personal site, linkedin profile, financial report |
include_domains | string | no | — | Comma-separated allowlist of domains. |
exclude_domains | string | no | — | Comma-separated denylist of domains. |
include_text | string | no | — | 5-word filter — only return pages that contain this exact phrase. |
exclude_text | string | no | — | 5-word filter — drop pages that contain this exact phrase. |
start_published_date | string | no | — | ISO 8601 date — only pages published after this. |
end_published_date | string | no | — | ISO 8601 date — only pages published before this. |
start_crawl_date | string | no | — | ISO 8601 — only pages crawled after this. |
end_crawl_date | string | no | — | ISO 8601 — only pages crawled before this. |
show_content | boolean | no | true | Show page content snippets in results. |
text | boolean | no | false | Return full page text. Honored when show_content=true. |
text_max_chars | number | no | — | Char cap on text. Empty = unlimited. |
include_html_tags | boolean | no | false | Preserve HTML structure in returned text. |
highlights | boolean | no | false | Return short highlight snippets. |
highlights_sentences | number | no | 3 | Sentences per highlight. · Range: 1 – 10 |
highlights_per_url | number | no | 3 | Highlights per result. · Range: 1 – 10 |
highlights_query | string | no | — | Custom phrase to highlight (different from main query). |
summary | boolean | no | false | Return a per-page summary. |
summary_query | string | no | — | Custom prompt for the summary (only when summary=true). |
subpages | number | no | 0 | Crawl this many subpages per result. · Range: 0 – 10 |
subpage_target | string | no | — | Keyword to bias subpage selection (e.g. ‘pricing’). |
livecrawl | enum | no | "fallback" | Live-crawl strategy. always: re-fetch every page. fallback: re-fetch only when index is stale. never: index only. preferred: try live then index. · Allowed: always, fallback, never, preferred |
code_tokens | enum | no | "dynamic" | Code-search only. Token budget per code result. · Allowed: dynamic, 5000, 10000, 20000 |
disable_formatting | boolean | no | false | Return raw upstream response. |
Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/exa-search.
