Exa Search
/v1/api/exa/searchRun 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.
Request body
Call this sync operation at its vendor-qualified URL. The model identity is encoded in the path; only operation-specific input fields belong in the request body.
The natural-language search query.
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
Default: auto
Number of results to return.
Range: 1 to 100
Default: 10
Optional hint about the kind of pages to prioritize.
Allowed values: company, research paper, news, personal site, financial report, people
Only return results from these domains.
Exclude results from these domains.
Only return results published on or after this ISO 8601 date.
Format: date-time
Only return results published on or before this ISO 8601 date.
Format: date-time
Content options to return alongside each result.
Return highlighted relevant snippets.
Return an AI-generated summary of the page.
Return the full page text.
JSON Schema used to synthesize a structured output from the results.
Instruction that guides how the structured output is generated.
Response Schema
A synchronous completed response contains exactly one outputs item with only data. Failed and timeout responses contain error and never outputs.
Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.
Current public run status.
Allowed values: pending, running, completed, failed, timeout
Public SandBase model name used for this run.
Present only for completed runs. Contains exactly one item whose only field is data.
Operation-specific business payload. This reference uses an empty object when no safe example can be confirmed.
Present only for failed or timeout runs. Contains a public error type and sanitized message.
Stable public error category.
Sanitized error message safe to show to clients.
Usage details when available.
API capabilities
Capabilities declared by the API registry.
Default: web-search
Execution mode declared by the API registry.
Default: sync
pending response
{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"pending","model":"exa/search"}
running response
{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"running","model":"exa/search"}
completed response
{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"completed","model":"exa/search","outputs":[{"data":{}}]}
failed response
{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"failed","model":"exa/search","error":{"type":"upstream_error","message":"upstream request failed"}}
timeout response
{"id":"f3d2e8a1-7c4b-4a12-9d2e-123456789abc","status":"timeout","model":"exa/search","error":{"type":"upstream_error","message":"upstream request failed"}}