The Price of Thinking: Reasoning Effort as a Model-Specific API Contract
arXiv cs.AIen
arXiv cs.AI
AI Global WirearXiv:2608.16956v1 Announce Type: new Abstract: API buyers purchase a dated contract, not a model name alone: the contract includes the requested and served model, reasoning-effort term or its omission, output rail, service product, prompt, and price schedule. We study the reasoning-effort term through a registered paired contrast of Sonnet 5 with explicit high effort against the same model with effort omitted, using 30 AIME 2026 items and five calls per item. Every paid attempt was assigned one frozen terminal category, and inference resampled items while retaining their repeated calls. Mean delivered cost was \$0.01031 per call higher under the explicit-high contract than under the omitted
This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.
Read the full story at arXiv cs.AI- Forskning
Related AI news
- Depth Enables Local Entropy: Quadratic Depth Dependence in Deep Variation-Norm ReLU RegressionarXiv cs.AI · August 19, 2026
- Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis RankingarXiv cs.AI · August 19, 2026
- KernelArc: A Multi-Agent Framework for GPU Kernel OptimizationarXiv cs.AI · August 19, 2026
- Synthesizing Feature Extractors: An Agentic Approach for Algorithm SelectionarXiv cs.AI · August 19, 2026
- PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMsarXiv cs.AI · August 19, 2026
- SkillEffect: Checked Lowering for Memory-Bounded Agent ToolsarXiv cs.AI · August 19, 2026