Model deprecation is when an AI provider retires or replaces a specific model version — for example, when OpenAI replaces gpt-4o with gpt-5, or when Perplexity upgrades from one Sonar version to another. Model deprecations can shift brand visibility behavior without any change in brand content, because the new model may have different training data, different response patterns, and different source preferences.Documentation Index
Fetch the complete documentation index at: https://docs.getcited.in/llms.txt
Use this file to discover all available pages before exploring further.
Why it matters
A model update can cause a brand’s mention rate to change overnight — not because the brand did anything differently, but because the underlying AI model changed how it generates answers. This is one of the noise sources that Cited monitors. Brands that see sudden metric shifts should check whether the AI provider recently updated its model before investigating content-level causes.How Cited uses it
Cited tracks which model version is used for each platform and documents changes when they occur. When a model is deprecated, Cited validates the replacement against historical data before switching. The specific models currently in use are documented in Which LLMs we track. Model changes are one of the known sources of measurement non-determinism.Related concepts
- Which LLMs we track — current model versions and rationale
- Non-determinism — model updates as a source of response variance
- Data freshness — interpreting metric shifts in context