What the site compares
AI Model Matrix normalizes public LLM API metadata into a small set of decision metrics: prompt price, completion price, context window, release date, and popularity rank. Prices are shown in USD per 1 million tokens so models can be compared on the same unit.
Price normalization
Prompt and completion prices are stored separately. When a page includes a workload example, the estimate uses 1 million input tokens and 500 thousand output tokens. The estimate is not a bill or guarantee; it is a standardized scenario for comparing model economics.
Missing or unstable metadata
Some model entries may have incomplete pricing, release, or context metadata. Models with unavailable pricing are kept out of cost-ranked lists when a numeric price is required. Ranking-only models can appear when popularity data exists but pricing metadata is not available.
Ranking and freshness
Hot models are ranked from current popularity signals. New models are marked when their release timestamp falls within the current seven-day window for the latest data update. The footer shows pricing data freshness so readers can tell when the underlying catalog was last refreshed.
Verification
AI Model Matrix is a comparison aid, not a contract or billing source. Provider prices, availability, limits, and model names can change, so production decisions should be verified against the provider dashboard or agreement before deployment.