Meta AI
Query Meta AI via Wire — the answer with its cited web sources and entities
POST
https://api.anakin.io/v1/wire/taskRun a prompt against Meta AI and get the answer with its cited web sources, de-duplicated domains, and detected entities. Runs on your own connected account (auth_mode: "required") — pass its credential_id. Run it with the meta_prompt action on POST /v1/wire/task.
Catalog: meta_ai · action_id: meta_prompt · Credits: 10 / call · Auth: required
Request Body
{
"action_id": "meta_prompt",
"credential_id": "11111111-2222-3333-4444-555555555555",
"params": { "prompt": "top project management tools in 2026", "include_sources": true }
}| Parameter | Type | Description |
|---|---|---|
action_id required | string | Set to meta_prompt |
credential_id required | string (UUID) | Your connected Meta account — from GET /v1/wire/identities |
params.prompt required | string | The question to ask Meta AI (max 8192 chars) |
params.include_sources | boolean | Return cited web sources + the de-duplicated domain list. Default true |
params.include_thinking | boolean | Also return Meta AI's intermediate reasoning steps. Default false |
params.wait_seconds | integer | How long to wait for the streamed answer (15–240). Default 120 |
Code Examples
curl -X POST https://api.anakin.io/v1/wire/task \
-H "X-API-Key: your_api_key" \
-H "Content-Type: application/json" \
-d '{
"action_id": "meta_prompt",
"credential_id": "11111111-2222-3333-4444-555555555555",
"params": { "prompt": "top project management tools in 2026", "include_sources": true }
}'import requests
res = requests.post(
'https://api.anakin.io/v1/wire/task',
headers={'X-API-Key': 'your_api_key'},
json={
'action_id': 'meta_prompt',
'credential_id': '11111111-2222-3333-4444-555555555555',
'params': {'prompt': 'top project management tools in 2026', 'include_sources': True},
},
)
job_id = res.json()['job_id']const res = await fetch('https://api.anakin.io/v1/wire/task', {
method: 'POST',
headers: { 'X-API-Key': 'your_api_key', 'Content-Type': 'application/json' },
body: JSON.stringify({
action_id: 'meta_prompt',
credential_id: '11111111-2222-3333-4444-555555555555',
params: { prompt: 'top project management tools in 2026', include_sources: true },
}),
});
const { job_id } = await res.json();Response
202 Accepted{ "status": "processing", "job_id": "…", "poll_url": "/v1/wire/jobs/…" }Poll GET /v1/wire/jobs/{id} until status: "completed":
{
"status": "completed",
"credits_used": 10,
"data": {
"status": "ok",
"data": {
"prompt": "…", "answer_text": "…", "answer_chars": 1840,
"conversation_id": "…", "response_ids": [],
"sources": [ { "url": "https://…", "domain": "…", "title": "…", "favicon": "https://…" } ],
"domains": ["asana.com", "monday.com"], "source_count": 12,
"entities": [], "entity_count": 5, "citation_count": 12
},
"meta": { "action_id": "meta_prompt", "catalog_slug": "meta_ai", "envelope_version": "v1" }
}
}| Field | Type | Description |
|---|---|---|
data.data.answer_text | string | The answer |
data.data.sources | array | Cited web sources — { url, domain, title, favicon } |
data.data.domains | string[] | De-duplicated cited domains — a compact share-of-voice signal |
data.data.source_count | integer | Number of cited sources |
data.data.entities | array | Entities Meta AI detected in the answer |
Auth required — omitting
credential_idreturns401 AUTH_REQUIRED. Premium engine: 10 credits/call. Raisewait_seconds(up to 240) for heavy web-search queries. Billed only on success.