Tools raise the cost per task for every model, but by very different amounts. Astra costs $0.27 per task with tools and $0.21 without, and Sol $0.06 and $0.05. Fable costs $4.20 with tools and $0.73 without, a 5.8× difference. The largest multiples are Qwen3.8 Max (0902, xhigh) at 28×, Gemini 3.8 Flash at 20× and MiMo-V2.6-Pro at 15×.
The cheapest way to reach a given score is often a smaller model with tools. Haiku with tools scores 49% at $0.07 per task, while Opus without tools scores 34% at $0.33.
