# Cost-Aware Contrastive Routing for LLMs

arXiv: https://arxiv.org/abs/2508.12491 · HTML: https://mlsanity.com/paper/2508.12491/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 74 of its 98 references that are in the map.
- First posted on arXiv 17 Aug 2025.

## Builds on (most cited first, 30 of 74)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Mixtral of Experts](https://mlsanity.com/paper/2401.04088/) (2024)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time](https://mlsanity.com/paper/2203.05482/) (2022)
- [BLEURT: Learning Robust Metrics for Text Generation](https://mlsanity.com/paper/2004.04696/) (2020)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [Editing Models with Task Arithmetic](https://mlsanity.com/paper/2212.04089/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [TIES-Merging: Resolving Interference When Merging Models](https://mlsanity.com/paper/2306.01708/) (2023)
- [BARTScore: Evaluating Generated Text as Text Generation](https://mlsanity.com/paper/2106.11520/) (2021)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Mixture-of-Experts with Expert Choice Routing](https://mlsanity.com/paper/2202.09368/) (2022)
- [Merging Models with Fisher-Weighted Averaging](https://mlsanity.com/paper/2111.09832/) (2021)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion](https://mlsanity.com/paper/2306.02561/) (2023)
- [Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing](https://mlsanity.com/paper/2404.14618/) (2024)

## Built on by (most cited first, 16 of 16)

- [Multi-Crit: Benchmarking Multimodal Judges on Pluralistic Criteria-Following](https://mlsanity.com/paper/2511.21662/) (2025)
- [R2-Router: A New Paradigm for LLM Routing with Reasoning](https://mlsanity.com/paper/2602.02823/) (2026)
- [SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks](https://mlsanity.com/paper/2607.00053/) (2026)
- [Explore Data Left Behind in Reinforcement Learning for Reasoning Language Models](https://mlsanity.com/paper/2511.04800/) (2025)
- [ParetoBandit: Budget-Paced Adaptive Routing for Non-Stationary LLM Serving](https://mlsanity.com/paper/2604.00136/) (2026)
- [Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation](https://mlsanity.com/paper/2606.04402/) (2026)
- [Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret](https://mlsanity.com/paper/2606.09668/) (2026)
- [Catalog-Native LLM: Speaking Item-ID Dialect with Less Entanglement for Recommendation](https://mlsanity.com/paper/2510.05125/) (2025)
- [SecureRouter: Encrypted Routing for Efficient Secure Inference](https://mlsanity.com/paper/2604.15499/) (2026)
- [Privacy-Preserving LLMs Routing](https://mlsanity.com/paper/2604.15728/) (2026)
- [Capability Self-Assessment in Large Language Models](https://mlsanity.com/paper/2606.00251/) (2026)
- [What Should a Skill Remember? Quality--Cost Trade-offs in Cost-Aware Skill Rewriting for Language Model Agents](https://mlsanity.com/paper/2606.09421/) (2026)
- [The Capability Frontier: Benchmarks Miss 82% of Model Performance](https://mlsanity.com/paper/2606.26836/) (2026)
- [n-Musketeers: Reinforcement Learning Shapes Collaboration Among Language Models](https://mlsanity.com/paper/2602.09173/) (2026)
- [Quantum Circuit Vision: Cost-Aware Evaluation of Visual AI Agents for Quantum Code Generation](https://mlsanity.com/paper/2607.10057/) (2026)
- [COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation](https://mlsanity.com/paper/2608.04336/) (2026)

## Abstract (arXiv)

We study cost-aware routing for large language models across diverse and dynamic pools of models. Existing approaches often overlook prompt-specific context, rely on expensive model profiling, assume a fixed set of experts, or use inefficient trial-and-error strategies. We introduce Cost-Spectrum Contrastive Routing (CSCR), a lightweight framework that maps both prompts and models into a shared embedding space to enable fast, cost-sensitive selection. CSCR uses compact, fast-to-compute logit footprints for open-source models and perplexity fingerprints for black-box APIs. A contrastive encoder is trained to favor the cheapest accurate expert within adaptive cost bands. At inference time, routing reduces to a single k-NN lookup via a FAISS index, requiring no retraining when the expert pool changes and enabling microsecond latency. Across multiple benchmarks, CSCR consistently outperforms baselines, improving the accuracy-cost tradeoff by up to 25%, while generalizing robustly to unseen LLMs and out-of-distribution prompts.