Generative Engine Optimization

Aggregate LLM mention metrics by dimension · GEO API

POST/geo/mentions/aggregated-metrics
$$$min $0.50

Aggregate LLM mentions of a domain or keyword across platform, location, language, source/search-result domains, and brand entities.

Request
curl https://api.unifapi.com/geo/mentions/aggregated-metrics \
  -H "Authorization: Bearer $UNIFAPI_KEY"
Overview

This operation is part of the GEO API in the generative engine optimization category. It uses the same Bearer token, request tracing, error model, and billing envelope as every UnifAPI endpoint, so agents can switch between platforms without custom per-vendor glue code.

Use it when a workflow needs GEO public data but should still keep one API key, one account balance, and one predictable JSON contract across social, live public-data sources.

Common agent workflows

  • Fetch canonical public GEO content for summarization, ranking, monitoring, or enrichment.
  • Attach engagement, author, media, and source metadata to an agent workflow.
  • Give an AI agent a stable GEO data source without building a per-platform integration.
  • Normalize GEO responses into the same UnifAPI envelope used across the catalog.
Response shape

Unified envelope, platform-native fields

  • Lookup responses return one canonical object in `data` with stable identifiers, source URLs where available, and platform-specific metadata normalized into predictable JSON.
  • The operation has a 500 credits ($0.50) minimum charge, so `billing.records_charged` can be higher than the visible records returned.
  • A not-found or invalid-input condition uses the unified UnifAPI error shape, so callers do not need special handling for each source platform.

Billing

This operation charges 1 credit per billable record, with a 500 credits ($0.50) operation minimum. Public responses include billing metadata with credits charged, records charged, and remaining workspace balance. Platform-caused failures can be refunded.

Errors and retries

Authentication, validation, rate-limit, not-found, and provider errors use the unified UnifAPI error format. Agents should log `request_id`, retry only retryable failures, and treat invalid API keys, disabled keys, and expired keys as the same public `unauthorized` error type.