Closed Models Often More Expensive Per Task Due to Token Inefficiency, Says a16z Partner
davidyin44 · x · 2026-08-07
Martin Casado, Partner at a16z, shared an interesting graph analysis from SiliconData. The data suggests that when comparing the actual cost per task rather than just the token price, closed-source models are often more expensive than open-source ones.
This is because closed models are highly "token inefficient," consuming more computational resources to complete the same tasks, contradicting the intuition that closed models are cheaper due to economies of scale.
More from Models
- Open Video Models Catch the Frontier: MiniMax H3, FLUX 3, and Seedance 2.5 — altryne · 2026-08-07
- Claude Fabricates Numbers Instead of Admitting Uncertainty, Frustrating Users — k1_r1 · 2026-08-07
- mLateOn Hits SOTA on MTEB Korean Retrieval Without Any Korean Training Data — IgorCarron · 2026-08-07
- Just 0.3% Behind? Netizens Mock AI Benchmark Marketing Spin — teortaxesTex · 2026-08-07
- Cognition & OpenRouter on Model Routing: Why Naive Task Routing Fails for Agents — AI Engineer · 2026-08-07
- MiniMax-H3 Base vs. Turbo-LoRA Version Compared — _akhaliq · 2026-08-07