Model Configuration
Set the LLM used for each analysis phase. Changes take effect within ~5 minutes (config cache).
Phase 1 Research
Verifies the article's factual claims against the live web before scoring.
Anthropic uses the model's built-in web search (Claude only).
Tavily fetches web snippets, then the chosen model synthesizes the verdicts.
Phase 2 Analysis
Scores the article across the eight veracity categories and returns the FVI score.
The provider determines the API endpoint, so the model family must match it.
Nightly Batch overrides
The overnight news agent uses the settings above by default. Enable this to run the
nightly batch on different (e.g. cheaper) models without changing interactive analysis.