anthropic
* This model's size is not published. The figure is the exact midpoint of the reported range 49B reported · confidence: reported .
A measured floor from text memorization. A widely repeated guess of ~20B sits BELOW this floor and is therefore probably wrong.
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...
The OpenRouter API truncates descriptions — read the full text at the source
Every id and name this model has been seen under — for matching it against another catalogue.