LLllmpulse
Prompts

Bulk-create prompts

Add prompts to a project in bulk (up to 100 per request). Validates the account prompt quota and skips duplicates. When the project does not run on the schedule (paused, or beyond the plan's project limit) the prompts are still created, and the response says so with tracked false, untracked_reason and a warning. New prompts get their first answers within about 24 hours. The first run is queued on creation and a nightly run at 00:00 Europe/Madrid picks up any prompt still without answers, as far as the account's allowance of AI answers for the cycle covers it. When the allowance left cannot give every new prompt one answer per enabled AI model, first_runs_wait_until gives the reset time when the rest run, with a warning. A pitch project holds at most 100 prompts in all, deleted ones included (ERR_LIMIT_REACHED past that), and the prompts of a launched pitch project are fixed, so adding one returns ERR_INVALID_PARAM with error.meta.reason pitch_prompts_frozen. Requires a read_write scope API key.

post/prompts

Request

  • Base URL
    https://api.llmpulse.ai/api/v1
  • URL
    https://api.llmpulse.ai/api/v1/prompts
  • Auth
    API key in header Authorization

Request body

project_idinteger required
promptsstring[] required
country_codestring required
language_codestring required

Response

Created

project_idinteger
createdinteger
skippedinteger
total_afterinteger
prompts_availableinteger
trackedboolean

Whether scheduled runs include the project the prompts were added to. False when it is paused or beyond the plan's project limit, so the new prompts do not run until that changes

untracked_reasonstring nullable

Why tracked is false: pitch_project, paused or project_limit. Null when tracked

warningstring nullable

What to do when tracked is false, or why some first runs wait when first_runs_wait_until is set. Null otherwise

first_runs_wait_untilstring date-time nullable

Set when the account's allowance of AI answers left this cycle cannot give every new prompt one answer per enabled AI model, so the rest run when the allowance resets at this time (00:00 Europe/Madrid). It counts this request's prompts against what was left when it arrived, not first runs other requests queued moments earlier. Null otherwise, when the allowance is unlimited, when tracked is false or when the account is not active

request_idstring

Changes

No recorded changes to this operation across all 32 revisions of this API.