Model Tradeoffs

Only configurations with published Artificial Analysis Intelligence, task-time, and task-cost measurements are plotted. Cost is Artificial Analysis's weighted average cost per Intelligence Index task. The fixed 100k-input, 20k-output request estimate remains in each model's details.

Muse Spark 1.2's contributor endpoint is separately priced at $0.10/M input and $0.20/M output tokens. It requires opting in to Meta data collection and is not used in the Artificial Analysis task-cost ranking above.

The routing table shows defaults; request-supplied weights can change the selected model.