Skip to main content
POST
/
research
/
v1
Create a new research request
curl --request POST \
  --url https://api.exa.ai/research/v1/research/v1 \
  --header 'Content-Type: application/json' \
  --data '{
  "model": "exa-research",
  "instructions": "What species of ant are similar to honeypot ants?"
}'
{
  "researchId": "01jszdfs0052sg4jc552sg4jc5",
  "model": "exa-research",
  "instructions": "What species of ant are similar to honeypot ants?",
  "status": "running"
}

Get your Exa API key

Body

application/json
​
instructions
string
required

Instructions for what you would like research on. A good prompt clearly defines what information you want to find, how research should be conducted, and what the output should look like.

Maximum length: 4096
​
model
enum<string>
default:exa-research

Research model to use. exa-research is faster and cheaper, while exa-research-pro provides more thorough analysis and stronger reasoning.

Available options:
exa-research-fast,
exa-research,
exa-research-pro
​
outputSchema
object

JSON Schema to enforce structured output. When provided, the research output will be validated against this schema and returned as parsed JSON.

Response

201 - application/json

Research request created

  • Pending
  • Running
  • Completed
  • Canceled
  • Failed
​
researchId
string
required

Unique identifier for tracking and retrieving this research request

​
createdAt
number
required

When the research was created (Unix timestamp in milliseconds)

​
instructions
string
required

The original research instructions provided

​
status
enum<string>
required
Available options:
pending
​
model
enum<string>
default:exa-research

The model used for this research request

Available options:
exa-research-fast,
exa-research,
exa-research-pro
​
outputSchema
object

The JSON Schema used to validate the output, if provided

⌘I