Metrics
Brand Perception by LLM Source
Shows how a brand's perception themes vary across different AI models (ChatGPT,
Gemini, Claude, etc.), revealing consistency or divergence in brand perception.
This endpoint breaks down a specific brand's cluster distribution by each AI source/LLM.
For example, ChatGPT might perceive Nike as 70% comfortable while Gemini sees it as only 10% comfortable. Critical for identifying perception inconsistencies across different AI platforms and understanding which LLMs favor which brand attributes.
**When to use:** User wants to analyze perception consistency across AI models, identify which LLMs have different brand perceptions, compare ChatGPT vs Gemini brand profiles, or validate brand positioning across multiple sources.
**Common user queries:**
- "How does Nike's perception differ between ChatGPT and Gemini?"
- "Show me cluster breakdown by LLM"
- "Compare brand perception across AI sources"
- "Which AI model sees Nike as most comfortable?"
- "Is brand perception consistent across different LLMs?"
- "Get source-specific cluster distribution"
**Returns:** Array of objects with brand, source, cluster, and share percentages.
Example: [{"brand": "Nike", "source": "chatgpt-4", "cluster": "Comfortable", "share": "0.70"},
{"brand": "Nike", "source": "gemini", "cluster": "Comfortable", "share": "0.10"}]
Required permission: `read:analysis`.
GET
Brand Perception by LLM Source
Path Parameters
Query Parameters
Filter by a list of persona IDs. Values should be comma separated, without brackets or spaces. The IDs are resolved to the persona labels recorded on the analysis, so this returns the same rows as the equivalent persona__in call. Use it for analyses that carry persona_ids; analyses predating persona records have none, and must be filtered with persona or persona__in. An ID that is not one of the analysis's personas matches no rows.
Filter by one specific source.
Available options:
claude-3-5-sonnet, claude-4-5-sonnet, claude-4-6-sonnet, claude-4-sonnet, deepseek-chat, deepseek-reasoner, deepseek-v3.2-maas, gemini-1.5-pro, gemini-2.0-flash, gemini-2.5-flash, gemini-2.5-flash-grounded, gemini-2.5-flash-lite, gemini-3-flash-preview, gemini-3.5-flash-lite, google-ai-mode, gpt-3.5-turbo, gpt-4-turbo, gpt-4o, gpt-4o-mini-search, gpt-5, gpt-5.2, gpt-5.4-mini, meta-llama-3.1-70B-instruct-turbo, meta-llama-3.2-70B-instruct-turbo, meta-llama-3.3-70B-instruct-turbo, meta-llama-4-maverick, mistral-7B-instruct, muse-spark-1.2, muse-spark-1.3, perplexity-sonar, rufus Filter by a list of sources. Values should be comma separated, without brackets or spaces
Available options:
claude-3-5-sonnet, claude-4-5-sonnet, claude-4-6-sonnet, claude-4-sonnet, deepseek-chat, deepseek-reasoner, deepseek-v3.2-maas, gemini-1.5-pro, gemini-2.0-flash, gemini-2.5-flash, gemini-2.5-flash-grounded, gemini-2.5-flash-lite, gemini-3-flash-preview, gemini-3.5-flash-lite, google-ai-mode, gpt-3.5-turbo, gpt-4-turbo, gpt-4o, gpt-4o-mini-search, gpt-5, gpt-5.2, gpt-5.4-mini, meta-llama-3.1-70B-instruct-turbo, meta-llama-3.2-70B-instruct-turbo, meta-llama-3.3-70B-instruct-turbo, meta-llama-4-maverick, mistral-7B-instruct, muse-spark-1.2, muse-spark-1.3, perplexity-sonar, rufus Response
Available options:
gpt-3.5-turbo, gpt-4-turbo, gpt-4o, gpt-4o-mini-search, gpt-5, gpt-5.2, gpt-5.4-mini, gemini-1.5-pro, gemini-2.0-flash, gemini-2.5-flash-grounded, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-3-flash-preview, gemini-3.5-flash-lite, meta-llama-3.1-70B-instruct-turbo, meta-llama-3.2-70B-instruct-turbo, meta-llama-3.3-70B-instruct-turbo, meta-llama-4-maverick, muse-spark-1.2, muse-spark-1.3, mistral-7B-instruct, claude-3-5-sonnet, claude-4-sonnet, claude-4-5-sonnet, claude-4-6-sonnet, deepseek-chat, deepseek-reasoner, deepseek-v3.2-maas, perplexity-sonar, rufus, google-ai-mode Brand Perception by LLM Source