Skip to main content
POST
Start Response Streaming

Authorizations

x-api-key
string
header
required

API key for authentication. You can create one here.

Body

application/json
website_id
string<uuid>
required

Website to run the response streaming for.

schedule_id
string<uuid>

Schedule UUID to attribute the run to and take prompt selectors from. Omit for Default. Explicit model, fan-out, persona and location options apply to this run. The schedule must belong to this website and must not be archived.

prompt_ids
string<uuid>[]

Specific prompts to run (1–1,000). Omit to run all active prompts for the website. Only active prompts are executed: paused prompt IDs are accepted (the run still returns 201) but are silently skipped and never queued, so pass active prompt IDs.

selected_models
object

Map of model id to enabled flag (e.g. { "ai_overview": true, "ai_mode": false }). Model ids: chatgpt, ai_overview (Google AI Overviews; google_ai_overview, its name in the model filters, is also accepted), perplexity, gemini, copilot, ai_mode, grok, claude, deepseek, meta_ai, mistral. Omit to run every currently active model — this is not the dashboard's saved default selection. An id set to true that names no model is rejected with 400, as is an explicit selection that resolves to no available models.

prompt_variations
integer

Number of paraphrased variations to generate per prompt (0–10).

Required range: 0 <= x <= 10
use_personas
boolean

Whether to run the prompts through configured personas.

use_locations
boolean

Whether to run the prompts across the website's configured locations.

only_locations
boolean

When true, skip the base (non-localized) run and execute only the location-scoped variants. Requires use_locations: true: sending only_locations: true without use_locations: true queues nothing (the base run is skipped and no location variants are added), so the run completes as a no-op.

Response

Run started

workflow_id
string
required
status
enum<string>
required
Available options:
running