Skip to main content

Builder Chat

POST 
/v2/auto/chat

Ask the AI to help you build an EQL query.

The response message contains the AI's reply in Markdown. When it generates EQL, it will be in a JSON code block that you can extract, validate, and submit.

Use sessionId in follow-up requests to maintain conversation context.

Cost​

API mode: 1 + dynamic credits

  • base request charge: 1 credit
  • dynamic usage charge: ceil(request_cost * 750) credits

In x402 mode, equivalent reference pricing remains:

  • fast: 5 credits ($0.045)
  • expert: 18 credits ($0.162)

Auth​

Required header:

x-elfa-api-key: <api_key>

This route does not require HMAC. Chat produces drafts only; any subsequent activation goes through POST /queries/drafts/{draftId}/convert, which gates trade-flavoured drafts behind HMAC.

Request Example​

{
  "message": "Alert me when BTC breaks 100k",
  "speed": "expert",
  "sessionId": "optional-session-id"
}

Response Example (200)​

{
  "sessionId": "session-uuid",
  "response": "I can help with that...",
  "title": "BTC Breakout Alert",
  "reasoning": null,
  "planIds": []
}

Best practice: persist sessionId and reuse it for follow-up prompts so the model keeps context across turns.

Request​

Responses​

Ok