mode:quick

When to use it

• You want the cheapest, fastest LLM-coverage check across 4 platforms in one call.
• You don't need fan-out queries or visual UI artifacts — the API answer is enough.
• You're polling on a schedule (use /v1/watch).

Pricing

150 credits per fresh call (5 on cache hits) regardless of how many of the 4 providers you fan out to. Partial-failure refund applies — if 3 of 4 providers succeed, you pay (3/4) × 150 = 113 credits (rounded up to the nearest whole credit).

SLA

Target 99% success rate, <5s p95 latency over the trailing 7 days. Live numbers at /v1/health.

Request

curl https://api.mentionsapi.com/v1/check \
  -H "Authorization: Bearer lvk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "quick",
    "query": "best CRM for small business",
    "brand": "HubSpot",
    "providers": ["chatgpt","claude","gemini","perplexity"]
  }'

City localisation & model override

Two quick-only request fields. city (1–80 chars) localises web search to a city on the engines that support it — ChatGPT and Claude — and is ignored by Gemini and Perplexity; pair it with region for the country. A city-localised answer is cached separately from the country-only one. models overrides the model per provider; each id is checked against the models currently available for that provider and an unknown one returns 400 invalid_model before anything is charged. Reasoning models (gpt-5 family, o-series, sonar-reasoning) are allowed. Omitted providers use the default model. Different models are cached separately.

curl https://api.mentionsapi.com/v1/check \
  -H "Authorization: Bearer lvk_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "mode": "quick",
    "query": "best CRM for small business",
    "brand": "HubSpot",
    "region": "us",
    "city": "Austin",
    "models": { "chatgpt": "gpt-5", "claude": "claude-sonnet-5" }
  }'

Unknown model → 400, nothing charged:

{
  "error": {
    "code": "invalid_model",
    "message": "gpt-9 is not available for chatgpt",
    "provider": "chatgpt",
    "model": "gpt-9"
  },
  "request_id": "req_01JBQ2K8H..."
}

Response

{
  "id": "chk_a8d2c...",
  "mode": "quick",
  "query": "best CRM for small business",
  "brand": "HubSpot",
  "providers": {
    "chatgpt":    { "mentioned": true, "rank": 6, "context": "...", "citations": [{ "url": "https://zapier.com/blog/best-crms/", "title": "Zapier", "text": "HubSpot CRM stands out for its free tier" }], "fan_out": [] },
    "claude":     { "mentioned": true, "rank": 4, "context": "...", "citations": [{ "url": "https://www.hubspot.com/crm", "title": "hubspot.com" }], "fan_out": [] },
    "gemini":     { "mentioned": true, "rank": 7, "context": "...", "citations": [{ "url": "https://www.g2.com/categories/crm", "title": "G2 CRM Reviews", "text": "HubSpot is a top-rated CRM for small teams" }], "fan_out": [] },
    "perplexity": { "mentioned": true, "rank": 6, "context": "...", "citations": [...], "fan_out": [] }
  },
  "duration_ms": 4218,
  "cost_cents": 150,
  "balance_after_cents": 9870,
  "cache_hit": false
}

Notes

• Citations: populated only when the LLM API returns them. Claude and Perplexity Sonar return citations more often than ChatGPT/Gemini.
• Cited text: ChatGPT and Gemini report which span of the answer each citation supports. It is returned as citations[].text (trimmed, ≤300 chars) and omitted when the engine gives no span — so you can tell which sentence a source backs, not just that it was cited.
• Sponsored: not returned in mode:quick — the API answers have no ad slot. Use mode:chatgpt_live, mode:ai_overview, mode:ai_mode or mode:bing_copilot to see paid placements.
• Fan-out: always empty in mode:quick — the official APIs don't expose the platform's fan-out queries. Use mode:chatgpt_live or mode:gemini_live for those.
• Web search: we enable web search on every provider that supports it (OpenAI's tool-call, Perplexity Sonar, etc.) so the answers reflect current data.
• Region: regional grounding is applied on ChatGPT, Claude and Perplexity. Gemini uses global grounding — the region parameter does not alter Gemini results. City-level localisation (city) applies to ChatGPT and Claude only.