Provided by DataForSEO
Get ChatGPT's Answer to One Prompt as Markdown (DataForSEO)
Ask ChatGPT one prompt from one location and language and read the answer it writes back as markdown, together with the model that answered and a check URL; optionally force it to look things up online before answering. One prompt in, one answer out. One request per call, priced by the vendor's own rate card; an empty result set is reported as no result.
How to run it
Step 1Set up
Once: paste this into your agent's chat. The Skill installs the CLI and logs in by itself. For an agent that cannot use a shell, connect it over MCP instead.
set up https://glasser.ai/SKILL.md
Show me how to use the DataForSEO endpoint /v3/ai_optimization/chat_gpt/llm_scraper/live/advanced on Glasser.glasser run -p dataforseo -e '/v3/ai_optimization/chat_gpt/llm_scraper/live/advanced' -i '{"keyword":"albert einstein","language_code":"en","location_code":2840}' --endpoint-version 6Uses endpoint version 6. Inspect the current price before running. Install and log in first on Get Started.
Once per Run:
IDEMPOTENCY_KEY=$(uuidgen)Run it, and copy this same block to send it again:
curl -X POST https://api.glasser.ai/v1/runs \
-H "Authorization: Bearer gl_..." \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-H "Content-Type: application/json" \
-d '{"provider":"dataforseo","endpoint":"/v3/ai_optimization/chat_gpt/llm_scraper/live/advanced","input":{"keyword":"albert einstein","language_code":"en","location_code":2840},"endpoint_version":6}'Reuse the same Idempotency-Key to send it again: the second send is a read of the first Run. A new key is a new Run and a new Charge. Uses endpoint version 6; inspect the current price before running.
Step 2Try a specific example task
When you need to report on brand visibility in AI responses, you might look for mentions of your brand in the available data and collect the supporting evidence.
Copy this prompt into your agent to review evidence for your AI visibility report.
Use dataforseo:/v3/ai_optimization/chat_gpt/llm_scraper/live/advanced on Glasser.
Find evidence of my brand in the returned AI visibility data for my monitoring report.Endpoint structure
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"keyword"
],
"properties": {
"tag": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"keyword": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"language_code": {
"type": "string",
"maxLength": 2048,
"minLength": 1
},
"language_name": {
"type": "string"
},
"location_code": {
"type": "integer"
},
"location_name": {
"type": "string"
},
"force_web_search": {
"type": "boolean"
}
},
"additionalProperties": false
}{
"keyword": "albert einstein",
"language_code": "en",
"location_code": 2840
}This Endpoint publishes no output schema. You get the Provider's own response body, unchanged — we do not warrant a shape we cannot guarantee.
How pricing works
| Data returned or no match | The same price with or without matching data. | $0.004 |
|---|---|---|
| Provider error | The Provider failed to answer. | $0.00 |
| Timed out | The Run exceeded its time limit. | $0.00 |
| Internal failure | An internal error prevented completion. | $0.00 |