Exa modelsapi generation api

exa/search

Name: Exa Search
Author: Exa

Run a neural semantic web search.. Search the open web with a natural-language query and get back the most relevant results, optionally with page contents inline.

Input

Query(string)

The natural-language search query.

Type(string)

Search mode. auto lets Exa choose; the deep modes trade latency for higher-quality retrieval. Allowed values: auto, fast, instant, deep-lite, deep, deep-reasoning.

Number of Results(integer)

1100

Number of results to return. Range: 1 to 100.

Category(string)

Optional hint about the kind of pages to prioritize. Allowed values: company, research paper, news, personal site, financial report, people.

Include Domains(array)

Only return results from these domains.

Exclude Domains(array)

Exclude results from these domains.

Start Published Date(string)

Only return results published on or after this ISO 8601 date. Format: ISO 8601 date and time.

End Published Date(string)

Only return results published on or before this ISO 8601 date. Format: ISO 8601 date and time.

Contents(object)

Content options to return alongside each result.

Output Schema(object)

JSON Schema used to synthesize a structured output from the results.

System Prompt(string)

Instruction that guides how the structured output is generated.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDexa/search

Input Schema

11 parameters · 1 required · 10 optional

Parameter	Type	Required	Description
`query`	string	Required	The natural-language search query.
`type`	string	Optional	Search mode. auto lets Exa choose; the deep modes trade latency for higher-quality retrieval. · Options: auto, fast, instant, deep-lite, deep, deep-reasoning · Default: "auto" autofastinstantdeep-litedeepdeep-reasoning
`category`	string	Optional	Optional hint about the kind of pages to prioritize. · Options: company, research paper, news, personal site, financial report, people companyresearch papernewspersonal sitefinancial reportpeople
`contents`	object	Optional	Content options to return alongside each result.
`numResults`	integer	Optional	Number of results to return. · Min: 1 · Max: 100 · Default: 10
`outputSchema`	object	Optional	JSON Schema used to synthesize a structured output from the results.
`systemPrompt`	string	Optional	Instruction that guides how the structured output is generated.
`excludeDomains`	string[]	Optional	Exclude results from these domains.
`includeDomains`	string[]	Optional	Only return results from these domains.
`endPublishedDate`	string	Optional	Only return results published on or before this ISO 8601 date.
`startPublishedDate`	string	Optional	Only return results published on or after this ISO 8601 date.

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Code Examples

Ready-to-run snippets

curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "exa/search",
  "type": "auto",
  "numResults": 10,
  "prompt": "a beautiful sunset over mountains"
}'

← Back to Exa Search

API README

Exa Search

Run a neural semantic web search. Search the open web with a natural-language query and get back the most relevant results, optionally with page contents inline. It is suitable for web-search workflows.

Capability

Run a neural semantic web search. Search the open web with a natural-language query and get back the most relevant results, optionally with page contents inline. It helps applications, agents, and automated workflows turn that capability into repeatable tasks and useful downstream experiences.

Common use cases

Search and discover relevant records for research, monitoring, and product experiences.
Create repeatable integrations that pass structured results to downstream business systems.
Support scheduled jobs, internal tools, and agent workflows with structured results.