AI Model Answer Check

See how an AI model answers a question, to check brand and product visibility. Call the AI Model Answer Check API via REST or MCP to automate SEO research.

CostRecent 10 credits / call

Try online

POST · https://api.nexscope.ai/seo/modelAnswerObservationMCP · nexscope_seo_model_answer_observation

Choose an integration method

AI Visibility

What this API does

See how an AI model answers a question, to check brand and product visibility. The request accepts prompt. Its documented result includes answerText, inputTokens, observedModel, outputTokens, prompt, reasoningTokens, requestedModel, webSearch.

AI Model Answer Check API use cases

Investigate AI Model Answer Check

To investigate ai model answer check, a search marketer submits prompt to AI Model Answer Check. The returned answerText, inputTokens, observedModel help investigate the requested operation.

Collect AI Model Answer Check evidence

A search marketer uses AI Model Answer Check with prompt to collect ai model answer check evidence. The returned answerText, inputTokens, observedModel help compare evidence for the requested scope.

Review AI Model Answer Check results

For this workflow, a search marketer calls AI Model Answer Check with prompt to review ai model answer check results. The result helps review the returned facts with the team.

AI Model Answer Check API FAQ

What does the AI Model Answer Check API return?

See how an AI model answers a question, to check brand and product visibility. The documented output includes answerText, inputTokens, observedModel, outputTokens, prompt, reasoningTokens, requestedModel, webSearch. It corresponds to the supplied prompt. Optional fields can be absent; a missing value should not be interpreted as a measured zero. Example values illustrate the response shape, rather than live account results.

How many credits does the AI Model Answer Check API cost?

The current documented cost is Recent 10 credits / call. This is the same cost shown at the top of this page. If a range or estimate is displayed, the final charge depends on the request. Review your available credits and the pricing page before calling the API, and check API usage records for the actual charge.

How do I call the AI Model Answer Check API from my app or an MCP client?

Send a POST request to https://api.nexscope.ai/seo/modelAnswerObservation with your API key as a Bearer token and the JSON inputs shown in API integration. In a compatible MCP client such as Claude or Cursor, connect Nexscope and call nexscope_seo_model_answer_observation. Use the MCP arguments shown in the MCP guide, or switch Online test to MCP to review its request before adding it to your app.

View plans and credits Connect this API with MCP

Try this API

Endpoint

https://api.nexscope.ai/seo/modelAnswerObservation

MCP method

nexscope_seo_model_answer_observation

Step 1 of 3 · Authenticate

Authentication

All run endpoints require a user API key. Send it as a bearer token in the Authorization header.

Authorization: Bearer nk-xxxxxxxxxxxxxxxxx

Missing or invalid API keys return an authentication error. Manage keys from .

Step 2 of 3 · Send a request

POSThttps://api.nexscope.ai/seo/modelAnswerObservation

Run an API

Send a JSON request body using the parameters described below.

Example request

Replace YOUR_API_KEY, then run this command in your terminal.

curl -X POST 'https://api.nexscope.ai/seo/modelAnswerObservation' \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "prompt": "nexscope"
}'

Step 3 of 3 · Inspect the result

Check the response

Read code for the request status and data for the result. Open the parameter and response reference for the full field definitions.

HTTP status codes

Code	Description
200	HTTP request completed. Check JSON code; only 0 indicates business success or acceptance.
400	Request JSON or required API parameters are invalid.
401	API key is missing, invalid, or cannot be matched to a user.
5xx	API execution or upstream service failed.

View parameters & response Try online

All categories/ AI Visibility

POSThttps://api.nexscope.ai/seo/modelAnswerObservation

Run this API

Send a JSON request to execute this API and receive the documented response payload.

Open tester

Endpoint

Method	`POST`
Path	`https://api.nexscope.ai/seo/modelAnswerObservation`
Auth	`Bearer API key`
Content-Type	`application/json`

Request parameters

Name	Type	Required	Description
`prompt`	`string`	required	Trim/NFC; Unicode code point limit500; newline and tab allowed. No tools/history/web options. Minimum length: 1 Maximum length: 500

Code example

{
  "prompt": "nexscope"
}

Response example

Example response envelope from the documented SEO API contract.

{
  "code": 0,
  "cost": "-1",
  "data": {
    "callId": "synthetic-call",
    "completedAt": null,
    "coverage": {
      "missing": [
        {
          "field": "synthetic",
          "reason": "UPSTREAM_FIELD_MISSING"
        }
      ],
      "status": "PARTIAL"
    },
    "requestedAt": "123",
    "result": {
      "answerText": "synthetic",
      "inputTokens": 9007199254740992,
      "meta": {
        "market": {
          "country": "synthetic",
          "language": "synthetic",
          "locationCode": 1
        },
        "missing": [
          {
            "path": "synthetic",
            "reason": "synthetic"
          }
        ],
        "missingOverflow": false,
        "retrievedAt": 9007199254740992,
        "sampledAt": 9007199254740992,
        "source": "synthetic",
        "truncated": false
      },
      "observedModel": "synthetic",
      "outputTokens": 9007199254740992,
      "prompt": "synthetic",
      "reasoningTokens": 9007199254740992,
      "requestedModel": "synthetic",
      "webSearch": false
    },
    "schemaVersion": "synthetic",
    "source": "synthetic",
    "status": "PARTIAL",
    "usage": {
      "billingStatus": "UNAPPROVED",
      "chargedCredits": "0"
    }
  },
  "msg": null,
  "time": "2026-01-01 00:00:00",
  "traceId": "synthetic-trace",
  "ts": "9007199254740993"
}

Response fields

Name	Type	Required	Description
`code`	`integer`	required	0 is a successful envelope; inspect data.status separately. Allowed: 0, 42008, 42009
`cost`	`string`	required	Elapsed processing milliseconds; not price. -1 for non-web context.
`data`	`object`	required	Data value used by this API operation.
`data.callId`	`string \| null`	optional	Call id value used by this API operation.
`data.completedAt`	`string \| integer \| null`	optional	Completed at value used by this API operation.
`data.coverage`	`object`	optional	Coverage value used by this API operation.
`data.coverage.missing`	`array`	optional	Missing value used by this API operation.
`data.coverage.missing[]`	`object`	required	Item in data coverage missing.
`data.coverage.missing[].field`	`string`	optional	Field value used by this API operation.
`data.coverage.missing[].reason`	`string`	optional	Reason value used by this API operation.
`data.coverage.status`	`string`	optional	Status value used by this API operation.
`data.requestedAt`	`string \| integer \| null`	optional	Requested at value used by this API operation.
`data.result`	`object \| null`	required	Result value used by this API operation.
`data.result.answerText`	`string \| null`	required	Answer text value used by this API operation. Maximum length: 65536
`data.result.inputTokens`	`integer \| null`	required	Input tokens value used by this API operation. Minimum: 0
`data.result.meta`	`object`	required	Meta value used by this API operation.
`data.result.meta.market`	`null`	required	Market value used by this API operation.
`data.result.meta.missing`	`array`	required	Missing value used by this API operation. Minimum items: 0 Maximum items: 100
`data.result.meta.missing[]`	`object`	required	Item in data result meta missing.
`data.result.meta.missing[].path`	`string`	required	Path value used by this API operation.
`data.result.meta.missing[].reason`	`string`	required	Reason value used by this API operation. Allowed: MISSING, NULL, INVALID, UNSUPPORTED, TRUNCATED
`data.result.meta.missingOverflow`	`boolean`	required	Missing overflow value used by this API operation.
`data.result.meta.retrievedAt`	`integer`	required	Retrieved at value used by this API operation. Minimum: 0 Maximum: 9007199254740991
`data.result.meta.sampledAt`	`integer \| null`	required	Sampled at value used by this API operation. Minimum: 0 Maximum: 9007199254740991
`data.result.meta.source`	`string`	required	Source value used by this API operation. Constant: DATAFORSEO_MODEL_API
`data.result.meta.truncated`	`boolean`	required	Truncated value used by this API operation.
`data.result.observedModel`	`string \| null`	required	Observed model value used by this API operation.
`data.result.outputTokens`	`integer \| null`	required	Output tokens value used by this API operation. Minimum: 0
`data.result.prompt`	`string`	required	Prompt value used by this API operation.
`data.result.reasoningTokens`	`integer \| null`	required	Reasoning tokens value used by this API operation. Minimum: 0
`data.result.requestedModel`	`string`	required	Requested model value used by this API operation. Constant: gpt-4.1-mini-2025-04-14
`data.result.webSearch`	`boolean \| null`	required	Web search value used by this API operation.
`data.schemaVersion`	`string \| null`	optional	Schema version value used by this API operation.
`data.source`	`string \| null`	optional	Source value used by this API operation.
`data.status`	`string`	optional	Status value used by this API operation. Allowed: SUCCESS, PARTIAL, EMPTY, PROCESSING, UNKNOWN, FAILED
`data.usage`	`object \| null`	optional	Usage value used by this API operation.
`data.usage.billingStatus`	`string \| null`	optional	Billing status value used by this API operation.
`data.usage.chargedCredits`	`string \| integer \| null`	optional	Charged credits value used by this API operation.
`msg`	`string \| null`	required	Available upstream msg/errmsg/message is preferred for success and failure; Chinese is translated to English. Missing successful message is null. Platform-only errors and task states use platform English. Message text never determines success or retry.
`time`	`string`	required	yyyy-MM-dd HH:mm:ss
`traceId`	`string \| null`	required	Trace id value used by this API operation.
`ts`	`string`	required	Epoch milliseconds; global long serializer.

Accepted processing response

code 0 confirms acceptance. Use data.callId to query the same request; processing is not completion.

Name	Type	Required	Description
`code`	`integer`	required	0 is a successful envelope; inspect data.status separately. Constant: 0
`cost`	`string`	required	Elapsed processing milliseconds; not price. -1 for non-web context.
`data`	`object`	required	Data value used by this API operation.
`data.callId`	`string \| null`	required	Call id value used by this API operation.
`data.reason`	`string`	required	Reason value used by this API operation. Constant: IN_PROGRESS
`data.retryable`	`boolean`	optional	Retryable value used by this API operation.
`data.status`	`string`	required	Status value used by this API operation. Constant: PROCESSING
`data.taskId`	`string \| null`	optional	Task id value used by this API operation.
`msg`	`string \| null`	required	Available upstream msg/errmsg/message is preferred for success and failure; Chinese is translated to English. Missing successful message is null. Platform-only errors and task states use platform English. Message text never determines success or retry.
`time`	`string`	required	yyyy-MM-dd HH:mm:ss
`traceId`	`string \| null`	required	Trace id value used by this API operation.
`ts`	`string`	required	Epoch milliseconds; global long serializer.

Error response

Name	Type	Required	Description
`code`	`integer`	required	0 is a successful envelope; inspect data.status separately.
`cost`	`string`	required	Elapsed processing milliseconds; not price. -1 for non-web context.
`data`	`object`	required	Data value used by this API operation.
`data.callId`	`string \| null`	required	Call id value used by this API operation.
`data.reason`	`string \| null`	required	Reason value used by this API operation.
`data.retryable`	`boolean`	optional	Retryable value used by this API operation.
`data.status`	`string \| null`	required	Status value used by this API operation.
`data.taskId`	`string \| null`	optional	Task id value used by this API operation.
`msg`	`string \| null`	required	Available upstream msg/errmsg/message is preferred for success and failure; Chinese is translated to English. Missing successful message is null. Platform-only errors and task states use platform English. Message text never determines success or retry.
`time`	`string`	required	yyyy-MM-dd HH:mm:ss
`traceId`	`string \| null`	required	Trace id value used by this API operation.
`ts`	`string`	required	Epoch milliseconds; global long serializer.

Retrieve a processing result

A response with PROCESSING and a callId means the result is still being prepared. Use the result query below with the returned identifier. This lookup reads the stored result and does not spend credits.

curl -X GET https://api.nexscope.ai/seo/modelAnswerObservation/calls/{callId} \
  -H "Authorization: Bearer nk-xxxxxxxxxxxxxxxxx"

Responses

Code	Description
200	HTTP request completed. Check JSON code; only 0 indicates business success or acceptance.
400	Request JSON or required API parameters are invalid.
401	API key is missing, invalid, or cannot be matched to a user.
5xx	API execution or upstream service failed.

Data source, freshness, and limitations

Source, freshness, coverage, rate limits, and estimation notes are not specified in this API definition unless they appear in the request or response field documentation above. Do not assume official marketplace data or real-time freshness when it is not explicitly documented.

Step 1 of 2 · Connect your MCP client

MCP

V2 recommended

Connect remote agents through the standard MCP 2025-11-25 Streamable HTTP endpoint. Use OAuth 2.1 Authorization Code with PKCE, or an API key for compatibility.

POST https://api.nexscope.ai/mcp
MCP-Protocol-Version: 2025-11-25
Content-Type: application/json

Authentication

OAuth clients request the mcp:tools scope. The endpoint's 401 response advertises protected-resource metadata for authorization discovery.

Step 2 of 2 · Call the tool

Call a tool

{
  "jsonrpc": "2.0",
  "id": "tool-call-1",
  "method": "tools/call",
  "params": {
    "name": "nexscope_seo_model_answer_observation",
    "arguments": {
      "prompt": "nexscope"
    }
  }
}

Legacy MCP v1

Existing API-key clients can continue using the compatibility endpoint. New integrations should use MCP v2.

GET / POST /mcp/legacy

Online test

Execute the current API with your API key and JSON payload. Online tests use this site's configured API environment; the Endpoint and copyable examples use the public integration address.

Uses your signed-in Nexscope session

SEO API Lab

SEO Model Answer Observation

See how an AI model answers a question, to check brand and product visibility. Call the AI Model Answer Check API via REST or MCP to automate SEO research.

Live request

Estimated 10 credits / callAPI usage records

Prompt

Trim/NFC; Unicode code point limit500; newline and tab allowed. No tools/history/web options.

Up to 500 characters

Live calls may use Data credits.

Processing result

If a request is still processing, use the returned identifier to retrieve its stored result. The tester recognizes the identifier automatically, and result queries do not spend credits.

Live response

Results

Your live result will appear here.

Complete the request fields above and run the API. No sample response is substituted.

Test with an API key or MCP

Estimated 10 credits / callAPI usage records

Try it

Send a real request with the same contract shown in the reference.

Endpoint

/seo/modelAnswerObservation

Processing result endpoint

https://api.nexscope.ai/seo/modelAnswerObservation/calls/{resultId}

MCP method

nexscope_seo_model_answer_observation

API key*

JSON payload*

cURL

curl -X POST \
  https://api.nexscope.ai/seo/modelAnswerObservation \
  -H "Authorization: Bearer nk-..." \
  -H "Content-Type: application/json" \
  -d '{ "prompt": "nexscope" }'

Response

No response yet. Run the request to see the response here.

Processing result

Use the identifier returned by Run request. The tester selects the correct result query automatically, and result queries do not spend credits.

Result identifier

Result response

No task result yet. Query the task to see the generated output here.

Related APIs

AI Search Citation Sample

Check which sources ChatGPT cites when it answers a query.

AI Mention Records

List AI answers that mention a brand, with cited sources and search references.

AI Target Metrics

Get AI answer visibility metrics for a brand or domain.

AI Target Comparison

Compare AI answer visibility across several brands or domains.