The brands and products ChatGPT actually names, pre-extracted from the answer as typed JSON: each entity carries a name and a type (product, software, company, ...). Skip the NER pipeline — count mention share straight off the response and see who wins the recommendation on every prompt.
4.8 · 33 reviews
The result.entities array is included in the base ChatGPT request — every brand or product the answer names, deduplicated and typed.
import requests
response = requests.post(
"https://api.cloro.dev/v1/monitor/chatgpt",
headers={
"Authorization": "Bearer sk_live_your_api_key_here",
"Content-Type": "application/json"
},
json={
"prompt": "what is the best crm for a small business",
"country": "US"
}
)
print(response.json()){
"success": true,
"result": {
"text": "For small businesses, the CRMs most often recommended are HubSpot, Pipedrive, and Zoho CRM...",
"entities": [
{
"type": "software",
"name": "HubSpot"
},
{
"type": "software",
"name": "Pipedrive"
},
{
"type": "software",
"name": "Zoho CRM"
}
]
}
} | Field | Type | Description |
|---|---|---|
| type | string | Entity type identifier (e.g. "product", "software", "company"). |
| name | string | Entity name or title as ChatGPT rendered it. |
Pick a plan that fits your volume. Price per credit drops as you scale.
Increased concurrency, overages on credits and credit discounts for annual contracts.
Know moreCredit cost per request varies by provider. The rates below apply to async/batch requests; sync requests add a +2 credit surcharge.
ChatGPT full response includes query fan-out, ads, and shopping data. Google News uses the same pricing as Google Search.
Brand names in prose are messy: abbreviations, possessives, product-line variants. Running your own NER over answer text means maintaining a model and a brand dictionary. The entities array gives you ChatGPT's own structured rendering of who it recommended — a stable key for counting.
Run your category prompts on a schedule, count how often each brand appears in `entities` across samples, and divide by total runs. That mention rate — trended over time and compared with competitors — is the core AI share-of-voice metric. See AI visibility tracking for the full methodology.
Entities are who the answer names; sources are which pages taught it that. A brand can be mentioned without being cited (and vice versa) — tracking both tells you whether your visibility comes from your own content or from third parties.
No — entities ship in the base 5-credit ChatGPT request alongside text, sources, and citation pills. See pricing for the full credit table.
Yes — entities are typed, so you can separate company mentions from product mentions in one pass. For commerce prompts where ChatGPT renders full product carousels with prices and merchants, use the ChatGPT Shopping API alongside.