compare_models
Ask one question across 2–5 Perplexity models, then compare shared citations and agreeing or divergent facts in a consolidated Markdown report.
Instructions
Ask one question across 2–5 Perplexity models (running concurrently when multiple PERPLEXITY_PROFILE_DIRS profiles or backend='api' are configured), compare shared citations and agreed/divergent key facts, and return a consolidated Markdown report (spooled to .txt if >= 15000 chars or output_file is set).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"query": "<query>"
},
"name": "compare_models"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Question or architecture/code comparison prompt to send to each model | |
| models | No | Optional list of 2-5 Perplexity models (defaults to GPT-6.1 Sol, Claude Sonnet 5.5, Gemini 4 Hydrogen). | |
| backend | No | Execution backend: 'auto' (uses official Perplexity Agent API if PERPLEXITY_API_KEY is configured and thread_url is omitted, otherwise browser Pro session), 'browser' (Playwright Pro UI), or 'api' (official HTTPS Agent API). | |
| sources | No | Optional source filter applied to every model in the comparison. | |
| no_cache | No | If true, bypasses the local response cache (default TTL 3600s, configurable via PERPLEXITY_CACHE_TTL_SECONDS) and forces a fresh search. | |
| output_file | No | Optional .txt file path to save the full answer to (regardless of length). Relative paths resolve inside the server's outputs directory. When omitted, answers at or above 15000 chars (configurable via PERPLEXITY_LONG_OUTPUT_CHARS) are automatically saved to a .txt file with an inline preview and path. | |
| verify_claims | No | If true (or PERPLEXITY_VERIFY_CLAIMS=1), fetches cited pages and checks key facts (numbers, dates, versions, names) for each claim, marking supported / weak / unverified. | |
| timeout_seconds | No | Optional timeout in seconds for waiting on the answer (defaults to server timeout, 900s / 15 minutes; max 1800s for very large code or multi-part responses). |