Cover Image

CoIn: Counting the Invisible Reasoning Tokens in Commercial Opaque LLM APIs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Guoheng, Wang, Ziyao, Tian, Bowei, Liu, Meng, Shen, Zheyu, He, Shwai, He, Yexiao, Ye, Wanghao, Wang, Yiting, Li, Ang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Predictive Auditing of Hidden Tokens in LLM APIs via Reasoning Length Estimation
by: Wang, Ziyao, et al.
Published: (2025)

Invisible Tokens, Visible Bills: The Urgent Need to Audit Hidden Operations in Opaque LLM Services
by: Sun, Guoheng, et al.
Published: (2025)

Fair Diagnosis: Leveraging Causal Modeling to Mitigate Medical Bias
by: Tian, Bowei, et al.
Published: (2024)

EdgeLoRA: An Efficient Multi-Tenant LLM Serving System on Edge Devices
by: Shen, Zheyu, et al.
Published: (2025)

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning
by: Wang, Yiting, et al.
Published: (2025)

MindCraft: How Concept Trees Take Shape In Deep Models
by: Tian, Bowei, et al.
Published: (2025)

Towards counterfactual fairness through auxiliary variables
by: Tian, Bowei, et al.
Published: (2024)

FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards
by: Wang, Ziyao, et al.
Published: (2026)

What Matters in Transformers? Not All Attention is Needed
by: He, Shwai, et al.
Published: (2024)

Prada: Black-Box LLM Adaptation with Private Data on Resource-Constrained Devices
by: Wang, Ziyao, et al.
Published: (2025)

Revisiting Federated Fine-Tuning: A Single Communication Round is Enough for Foundation Models
by: Wang, Ziyao, et al.
Published: (2024)

Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
by: Wang, Ziyao, et al.
Published: (2026)

FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
by: Wang, Ziyao, et al.
Published: (2024)

CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications
by: Ye, Wanghao, et al.
Published: (2025)

VeriReason: Reinforcement Learning with Testbench Feedback for Reasoning-Enhanced Verilog Generation
by: Wang, Yiting, et al.
Published: (2025)

MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization
by: Wang, Yiting, et al.
Published: (2025)

Cognibit: From Digital Exhaustion to Real-World Connection Through Gamified Territory Control and LLM-Powered Twin Networking
by: Ye, Wanghao, et al.
Published: (2026)

EvoVerilog: Large Langugage Model Assisted Evolution of Verilog Code
by: Guo, Ping, et al.
Published: (2025)

SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
by: He, Yexiao, et al.
Published: (2024)

ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models
by: Sun, Guoheng, et al.
Published: (2026)

Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers
by: He, Shwai, et al.
Published: (2024)

Demystifying When Pruning Works via Representation Hierarchies
by: He, Shwai, et al.
Published: (2026)

Dense Video Understanding with Gated Residual Tokenization
by: Zhang, Haichao, et al.
Published: (2025)

MedOrch: Medical Diagnosis with Tool-Augmented Reasoning Agents for Flexible Extensibility
by: He, Yexiao, et al.
Published: (2025)

MoEless: Efficient MoE LLM Serving via Serverless Computing
by: Yu, Hanfei, et al.
Published: (2026)

Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration
by: He, Shwai, et al.
Published: (2024)

Understanding and Harnessing Sparsity in Unified Multimodal Models
by: He, Shwai, et al.
Published: (2025)

NeuroSymAD: A Neuro-Symbolic Framework for Interpretable Alzheimer's Disease Diagnosis
by: He, Yexiao, et al.
Published: (2025)

Making Large Language Models Efficient Dense Retrievers
by: Lei, Yibin, et al.
Published: (2025)

Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques
by: He, Shwai, et al.
Published: (2024)

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
by: He, Shwai, et al.
Published: (2025)

CoIn3D: Revisiting Configuration-Invariant Multi-Camera 3D Object Detection
by: Kuang, Zhaonian, et al.
Published: (2026)

Nanomolding single-crystalline CoIn3 and RhIn3 nanowires
by: Duong, Nghiep Khoan, et al.
Published: (2025)

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
by: Yao, Zhewei, et al.
Published: (2025)

SCARA: A Semantics-Constrained Autonomous Remediation Agent for Opaque Industrial Software Vulnerabilities
by: Ning, Bowei, et al.
Published: (2026)

Towards Building Non-Fine-Tunable Foundation Models
by: Wang, Ziyao, et al.
Published: (2026)

Token-Efficient Change Detection in LLM APIs
by: Chauvin, Timothée, et al.
Published: (2026)

Domino: Eliminating Communication in LLM Training via Generic Tensor Slicing and Overlapping
by: Wang, Guanhua, et al.
Published: (2024)

Beyong Tokens: Item-aware Attention for LLM-based Recommendation
by: Zhang, Xiaokun, et al.
Published: (2026)

Model-GLUE: Democratized LLM Scaling for A Large Model Zoo in the Wild
by: Zhao, Xinyu, et al.
Published: (2024)