POST /v1/check · mode reference

mode:all_live

The bundle. One call, six live AI search surfaces fanned out in parallel. Returns per-surface results in a single envelope so you can compare brand presence across Perplexity, ChatGPT, Gemini, Google AI Overview, Google AI Mode, and Bing Copilot in one shot.

Why use it

Discount. Component price would be 25 + 10 + 10 + 5 + 10 + 5 = 65¢; the bundle is 50¢ — 23% cheaper than calling each separately.
Latency stacking. The 6 calls run in parallel via Promise.allSettled. p95 latency tracks max(per-mode p95) ≈ 30s, not sum (which would be ~80s).
Single billing event. One charge, one wallet deduction, one usage_event row. Easier to reason about than 6 separate calls.

Pricing & refund

$0.50 per call. Partial-failure refund applies — if k of 6 surfaces succeed, you pay (k / 6) × 50¢. Examples:

6 of 6 succeed → 50¢
4 of 6 succeed → (4/6) × 50¢ = 33¢
2 of 6 succeed → (2/6) × 50¢ = 16¢
0 of 6 succeed → 0¢ (full refund)

SLA

Target 95% rate of "≥5 of 6 surfaces returned" — the bundle is meant to give you broad coverage, not 100% per-surface reliability. Any surface that fails surfaces under errors with a typed code; the bundle still 200s.

Request

bash

curl https://api.mentionsapi.com/v1/check \
  -H "Authorization: Bearer lvk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "all_live",
    "query": "best CRM for small business",
    "brand": "HubSpot"
  }'

Response — all 6 succeeded

json

{
  "id": "chk_a8d2c...",
  "mode": "all_live",
  "providers": {
    "perplexity":   { "mentioned": true, "rank": 6, "context": "...", "citations": [...10 items], "fan_out": [...5 items] },
    "chatgpt":      { "mentioned": true, "rank": 4, "context": "...", "citations": [...4 items], "fan_out": [...3 items], "brand_entities": [...] },
    "gemini":       { "mentioned": true, "rank": 5, "context": "...", "citations": [...6 items], "fan_out": [...4 items], "brand_entities": [...] },
    "ai_overview":  { "mentioned": true, "rank": 3, "context": "...", "citations": [...8 items], "fan_out": [], "brand_entities": [] },
    "ai_mode":      { "mentioned": true, "rank": 2, "context": "...", "citations": [...5 items], "fan_out": [], "brand_entities": [] },
    "bing_copilot": { "mentioned": true, "rank": 4, "context": "...", "citations": [...7 items], "fan_out": [], "brand_entities": [] }
  },
  "duration_ms": 28041,
  "cost_cents": 50,
  "balance_after_cents": 9948,
  "cache_hit": false
}

Response — partial success

Two upstream surfaces failed. The bundle still 200s; failures surface under errors and the price is prorated to (4 / 6) × 50¢ = 33¢.

json

{
  "mode": "all_live",
  "providers": {
    "perplexity":  { "mentioned": true, "rank": 6, ... },
    "chatgpt":     { "mentioned": true, "rank": 4, ... },
    "ai_overview": { "mentioned": false, "rank": null, ... },
    "bing_copilot":{ "mentioned": true, "rank": 4, ... }
  },
  "errors": {
    "gemini":  { "error": "upstream_rate_limited" },
    "ai_mode": { "error": "upstream_timeout" }
  },
  "cost_cents": 33,
  "balance_after_cents": 9967
}

Notes

Idempotency: retry the bundle with the same Idempotency-Key within 24h to replay the original response without re-charging.
Watches: use mode:all_live with /v1/watch to monitor brand presence across the full AI search universe on a schedule.
Per-surface dive: if you only need one surface, call its dedicated mode (cheaper). The bundle is for when you want the full picture in one call.