anthropic
* This model's size is not published. The figure is the exact midpoint of the reported range 980B–1.6T · confidence: speculation .
Reverse-engineered from cross-provider token throughput by one analyst (active parameters put at ~98–110B). Wide error bars.
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
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.