Overview
Answer-Engine / Generative-Engine Optimization. Company-scoped; requiresAuthorization: Bearer nv_sk_…. Pay-per-use via our data provider. MCP equivalents: naive_aeo_discover + naive_aeo_execute(_async).
LLM Responses (ChatGPT/Claude/Gemini) offer Live + Standard …/task; Perplexity is Live-only. LLM Scraper, AI Keywords, and LLM Mentions are Live.
REST callers: LLM Responses require
user_prompt (string, ≤500 chars) and model_name; the CLI maps --keyword → user_prompt. Each platform accepts only its own models — use GET .../{platform}/models to list them — and when --model is omitted the CLI supplies a valid per-platform default (chatgpt→gpt-4o-mini, claude→claude-sonnet-4-5, gemini→gemini-2.5-flash, perplexity→sonar). Do not send location/language to LLM Responses. LLM Mentions require target as an ARRAY OF OBJECTS, each { "keyword": "..." } or { "domain": "example.com" }, e.g. { "target": [{ "domain": "example.com" }] }; a top-level keyword or domain string is invalid.