Tool use cost overhead varies wildly: Qwen3.8 Max pays 28× per task, GPT-6 models barely 1.3×
ArtificialAnlys · x · 2026-11-12
Artificial Analysis breaks down how tool use affects per-task cost on VIALS-AA: tools raise costs for every model, but by wildly different multiples.
- Qwen3.8 Max (0902, xhigh) sees a 28× cost increase with tools, Gemini 3.8 Flash 20×, MiMo-V2.6-Pro 15×
- Claude Fable 5.2 goes from $0.73 to $4.20 (5.8×), while GPT-6 Astra only rises from $0.21 to $0.27 and Sol from $0.05 to $0.06
- The cheapest path to a given score is often a smaller model with tools: Haiku with tools scores 49% at $0.07/task vs tool-less Opus at 34% for $0.33
More from Infra
- AMD surges 11% on unverified report Nvidia board prepares to oust CEO Jensen Huang — Polymarket · 2026-11-12
- celld self-hosts Workers, Durable Objects and queues using just an object store bucket — irvinebroque · 2026-11-12
- Azar: transparent chip diffusion strategy backfired as China pivots models to Huawei chips — beffjezos · 2026-11-12
- Running a minimal local agent on 24GB RAM: Pi Agent + Bonsai 2 9B hits ~30 tok/s — Potential_Block4598 · 2026-11-12
- DigitalOcean: Many LLM Serving "Wins" Are Noise — One +4% Winner Wasn't Real — AI Engineer · 2026-11-12
- Homemade inference box pairs AMD CPUs with Huawei Ascend 950PR NPUs — AIFlow_ML · 2026-11-12