# Cost Trade-offs of Reasoning and Non-Reasoning Large Language Models in Text-to-SQL

arXiv: https://arxiv.org/abs/2512.22364 · HTML: https://mlsanity.com/paper/2512.22364/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 26 Dec 2025.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 18 of 18)

- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction](https://mlsanity.com/paper/2304.11015/) (2023)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows](https://mlsanity.com/paper/2411.07763/) (2024)
- [CodeS: Towards Building Open-source Language Models for Text-to-SQL](https://mlsanity.com/paper/2402.16347/) (2024)
- [MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL](https://mlsanity.com/paper/2312.11242/) (2023)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [Neo: A Learned Query Optimizer](https://mlsanity.com/paper/1904.03711/) (2019)
- [SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning](https://mlsanity.com/paper/2504.08600/) (2025)
- [An End-to-End Learning-based Cost Estimator](https://mlsanity.com/paper/1906.02560/) (2019)
- [XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL](https://mlsanity.com/paper/2507.04701/) (2025)
- [LLM-R2: A Large Language Model Enhanced Rule-based Rewrite System for Boosting Query Efficiency](https://mlsanity.com/paper/2404.12872/) (2024)
- [Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL](https://mlsanity.com/paper/2504.15077/) (2025)
- [Towards Optimizing SQL Generation via LLM Routing](https://mlsanity.com/paper/2411.04319/) (2024)
- [ABACUS: A FinOps Service for Cloud Cost Optimization](https://mlsanity.com/paper/2501.14753/) (2024)
- [BigBird: Big Data Storage and Analytics at Scale in Hybrid Cloud](https://mlsanity.com/paper/2203.11472/) (2022)

## Built on by (most cited first, 2 of 2)

- [CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment](https://mlsanity.com/paper/2606.04645/) (2026)
- [BAP-SQL: Budget-Aware Observation Planning for Agentic Text-to-SQL](https://mlsanity.com/paper/2608.02876/) (2026)

## Abstract (arXiv)

While Text-to-SQL systems achieve high accuracy, existing efficiency metrics like the Valid Efficiency Score prioritize execution time, a metric we show is fundamentally decoupled from consumption-based cloud billing. This paper evaluates cloud query execution cost trade-offs between reasoning and non-reasoning Large Language Models by performing 180 Text-to-SQL query executions across six LLMs on Google BigQuery using the 230 GB StackOverflow dataset. Our analysis reveals that reasoning models process 44.5% fewer bytes than non-reasoning counterparts while maintaining equivalent correctness at 96.7% to 100%, and that execution time correlates weakly with query cost at r=0.16, indicating that speed optimization does not imply cost efficiency. Non-reasoning models also exhibit extreme cost variance of up to 3.4×, producing outliers exceeding 36 GB per query, over 20× the best model's 1.8 GB average, due to missing partition filters and inefficient joins. We identify these prevalent inefficiency patterns and provide deployment guidelines to mitigate financial risks in cost-sensitive enterprise environments.