Cost-Optimal Foundation Model Deployment Portfolio for Transportation Management
Quick Answer
The study presents the Foundation Model Deployment Portfolio (FMDP) problem for optimizing model deployment in transportation management centers, achieving a cost of $34/month—97% lower than the all-closed-API baseline—by utilizing open-source APIs for four functions.
Quick Take
A polynomial-time greedy heuristic is proposed, with break-even analysis indicating on-premise GPU investment is viable only above 309 vision queries/hour or if API prices double.
Key Points
- FMDP minimizes total cost of ownership while meeting quality and latency constraints.
- The problem is proven NP-hard, reducing from the 0-1 knapsack problem.
- A case study with five TMC functions identified a mixed portfolio costing $34/month.
- Four functions were routed to open-source APIs, one to a closed API.
- On-premise GPU investment is reasonable only above 309 vision queries/hour.
DeepSignal Analysis
What happened
The study introduces the Foundation Model Deployment Portfolio (FMDP) problem, focusing on optimizing model deployment in transportation management centers. It achieves a monthly cost of $34, significantly lower than the baseline by using open-source APIs for most functions. A polynomial-time greedy heuristic is proposed to tackle this NP-hard problem.
Key evidence
- The FMDP problem is formulated as a mixed-integer program that minimizes total cost of ownership while adhering to quality, latency, and safety constraints.
- In a case study, the mixed portfolio identified by FMDP costs $34/month, which is 97% lower than the cheapest all-closed-API option.
- Break-even analysis indicates that on-premise GPU investment is justifiable only if vision queries exceed 309 per hour or if API prices double.
Why it matters
This research highlights the potential for significant cost savings in transportation management through the strategic deployment of foundation models. By optimizing model selection and deployment modes, organizations can enhance operational efficiency while maintaining quality and safety standards. The findings also suggest a shift towards open-source solutions, which could democratize access to advanced AI capabilities in the sector.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Foundation models, including large language models (LLMs) and vision-language models (VLMs), are increasingly used for transportation management center (TMC) tasks such as anomaly detection, incident reporting, and traveler information. Deploying multiple such models across TMC functions raises a portfolio question: which model should serve each function, in which deployment mode, and under what shared hardware budget? We formulate this as the Foundation Model Deployment Portfolio (FMDP) problem, a mixed-integer program minimizing total cost of ownership (TCO) subject to per-function quality, latency, and safety constraints over shared GPU capacity. We prove the problem NP-hard by reduction from the 0-1 knapsack problem and propose a polynomial-time greedy heuristic. In an illustrative case study with five TMC functions and 19 candidate (model, mode) pairs, FMDP identifies a mixed portfolio costing $34/mo (97% below the cheapest feasible all-closed-API baseline) by routing four functions to open-source APIs and the one function whose quality floor no open-source model meets to a closed API. Break-even analysis shows that on-premise GPU investment becomes reasonable only above approximately 309 vision queries/hour or if API prices double.
| Comments: | Accepted at IEEE ITSC 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.13239 [cs.AI] |
| (or arXiv:2607.13239v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.13239 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xi Cheng [view email]
[v1]
Tue, 14 Jul 2026 20:01:15 UTC (18 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.