Monitor brand mentions across ChatGPT, Perplexity, Gemini, and Google AI Overview. Get parsed citations and sources via one API — global country targeting.
curl -X POST https://api.cloro.dev/v1/monitor/chatgpt \
-H "Authorization: Bearer sk_live_your_api_key_here" \
-H "Content-Type: application/json" \
-d '{
"prompt": "best project management software for remote teams",
"country": "US",
"include": {
"markdown": true,
"sources": true
}
}' {
"success": true,
"result": {
"text": "...",
"sources": [],
"html": "...",
"markdown": "...",
"searchQueries": [],
"shoppingCards": [],
"entities": []
}
}
Currently supporting the major SEO and AI SEO providers.
Ready for any scale, across multiple regions.
Direct LLM API integration has hidden costs and difficult scalability.
Direct provider APIs don't give the tools to influence SEO.
Each provider requires separate API integration, creating technical overhead.
Token-based pricing varies by model and provider, making costs unpredictable.
Easily extract markdown, text or HTML. We parse the relevant objects of each response, such sources, citations, query fan-out, shopping and others.
import requests
# One query. Four AI engines. One credit pool.
prompts = ["best project management software for remote teams"]
engines = ["chatgpt", "perplexity", "gemini", "aimode"]
for engine in engines:
response = requests.post(
f"https://api.cloro.dev/v1/monitor/{engine}",
headers={
"Authorization": "Bearer sk_live_your_api_key_here",
"Content-Type": "application/json",
},
json={
"prompt": prompts[0],
"country": "US",
"include": {"sources": True, "markdown": True},
},
)
data = response.json()
print(f"{engine}: {len(data['result']['sources'])} sources cited"){
"success": true,
"result": {
"text": "For remote teams, the most-recommended project management tools...",
"sources": [
{
"position": 1,
"url": "https://asana.com/use-cases/remote-work",
"label": "Remote work — Asana",
"description": "How distributed teams stay aligned with Asana..."
}
],
"html": "<div class=\"markdown\"><p>For remote teams, the most-recommended project...</div>",
"markdown": "For remote teams, the most-recommended project management tools...",
"searchQueries": [
"best project management 2026",
"Asana vs Linear vs ClickUp"
],
"shoppingCards": [],
"entities": [
{
"name": "Asana",
"type": "product"
}
]
}
} Plans for all needs, with lowering price per credit as you scale.
Each provider requires different credit amounts per request. Prices below apply to async/batch requests, sync include a +2 credit surcharge.
Google News uses the same pricing as Google Search.
Our API delivers structured responses in 30-45 seconds on average. We handle all the complexity of automation and parsing to give you clean markdown content and citations in near real-time.
We extract the complete AI response in parsed markdown format, all source & citations with URLs and labels. Everything is delivered as structured JSON for easy integration into your systems.
We support ChatGPT (with Web Search), Google Gemini, Perplexity, Microsoft Copilot, Google AI Overview, and Google Search. Our unified API lets you extract data from all these sources using a consistent interface.
Yes! We offer an async endpoint that allows you to submit tasks and receive the results via webhook. This is ideal for high-volume scraping and ensures reliability without keeping connections open.
Concurrency limits depend on your subscription plan. For example, business plans often start with higher concurrency limits (e.g., 100). If you exceed your limit, you will receive a 429 status code. We recommend implementing client-side queuing or using our async endpoint.
You can increase your concurrency by subscribing to an higher-volume package. Since we dedicate resources exclusively to your organization, we want to ensure those resources are fully utilized and not just spiky traffic. However, if you are indeed limited by concurrency (constantly using your concurrency more than 70% of the time), you should contact us so we can adjust.
Yes. By default, we return parsed structured JSON to keep responses lightweight. However, you can retrieve the full raw HTML of the result page by setting include.html: true in your request.
Yes, we support all countries globally. Note that some models (like Gemini) may have regional availability restrictions (e.g., EU).
You generally don't need to implement complex timeout logic. Our system automatically retries requests up to 10 times with a maximum duration of 5 minutes to ensure high success rates.
Credits are deducted only when we successfully extract and deliver AI response data. Failed extractions or system errors do not consume your credits.
No, credits do not roll over from month to month. Each billing cycle, you receive your allocated credits based on your subscription plan. Any unused credits expire at the end of the billing period.
We accept all major credit cards for self-service plans. For Enterprise accounts, we work with bank transfers (ACH/Wire).
Our service goes beyond just the API: we strive to provide the best customer support and short feedback cycles. This is why we decided to set a minimum tier that ensures everyone receives quality support. This approach allows us to focus on delivering exceptional value to customers who are serious about scaling their operations.
We do not offer refunds. We offer some free credits precisely for the purpose of testing. For self-service plans, you may cancel at any time and your access will continue until the end of your current billing period. For full details, please review our Terms of Service.
Monitor your brand and your competitors, at global scale and with the best performance.
No credit card required.