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

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

19 May 2025arXiv:2505.13778archive 2025-07-28

Guoheng Sun, Ziyao Wang, Bowei Tian, Meng Liu, Zheyu Shen, Shwai He, Yexiao He, Wanghao Ye, Yiting Wang, Ang Li

As post-training techniques evolve, large language models (LLMs) are increasingly augmented with structured multi-step reasoning abilities, often optimized through reinforcement learning. These reasoning-enhanced models outperform standard LLMs on complex tasks and now underpin many commercial LLM APIs. However, to protect proprietary behavior and reduce verbosity, providers typically conceal the reasoning traces while returning only the final answer. This opacity introduces a critical transparency gap: users are billed for invisible reasoning tokens, which often account for the majority of the cost, yet have no means to verify their authenticity. This opens the door to token count inflation, where providers may overreport token usage or inject synthetic, low-effort tokens to inflate charges. To address this issue, we propose CoIn, a verification framework that audits both the quantity and semantic validity of hidden tokens. CoIn constructs a verifiable hash tree from token embedding fingerprints to check token counts, and uses embedding-based relevance matching to detect fabricated reasoning content. Experiments demonstrate that CoIn, when deployed as a trusted third-party auditor, can effectively detect token count inflation with a success rate reaching up to 94.7%, showing the strong ability to restore billing transparency in opaque LLM services. The dataset and code are available at https://github.com/CASE-Lab-UMD/LLM-Auditing-CoIn.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2505.13778")

Code

Syntology Ran 0 of 18 code samples harvested from 1 repository linked to this paper; 18 have no recorded run.

By repository: official repository: 18 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

case-lab-umd/llm-auditing-coin officialmentioned in paperpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

18 samples harvested; 0 ran; 0 honoured the contract we drafted; 18 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

18unverified

Licence: 0 of the 18 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from case-lab-umd/llm-auditing-coin. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

circle_loss case-lab-umd/llm-auditing-coin/3_Block2Answer/train/loss_func.py official repository unverified MIT (permissive) · 191c319131abd458 · report
construct_flat_merkle_tree case-lab-umd/llm-auditing-coin/2_hash_tree/main_eval.py official repository unverified MIT (permissive) · f002064d6028a788 · report
construct_prompt case-lab-umd/llm-auditing-coin/6_discussion/LLM_predict.py official repository unverified MIT (permissive) · 2843e3f35ce11d01 · report
construct_prompt case-lab-umd/llm-auditing-coin/6_discussion/LLM_reconstruct.py official repository unverified MIT (permissive) · 577fc0eeba8dfc18 · report
contrastive_loss case-lab-umd/llm-auditing-coin/3_Block2Answer/train/loss_func.py official repository unverified MIT (permissive) · 37e51a6ba577d8d9 · report
extract_think_and_solution_V2 case-lab-umd/llm-auditing-coin/0_preprocess/train_eval.py official repository unverified MIT (permissive) · 0bdd5673fd4522a4 · report
extract_think_sections case-lab-umd/llm-auditing-coin/0_preprocess/train_eval.py official repository unverified MIT (permissive) · ecfef8a7e8d9d7da · report
focal_loss case-lab-umd/llm-auditing-coin/3_Block2Answer/train/loss_func.py official repository unverified MIT (permissive) · d00ea9e4c5542ee7 · report
generate_merkle_proof case-lab-umd/llm-auditing-coin/2_hash_tree/verify.py official repository unverified MIT (permissive) · b07a313f5559ca17 · report
get_matching_head case-lab-umd/llm-auditing-coin/5_CoIn_pipline/heads.py official repository unverified MIT (permissive) · 755711dbf05419ed · report
hash_data case-lab-umd/llm-auditing-coin/2_hash_tree/main_eval.py official repository unverified MIT (permissive) · 081cd788e89c4c62 · report
hash_data case-lab-umd/llm-auditing-coin/2_hash_tree/verify.py official repository unverified MIT (permissive) · e706f25280079c8b · report
preprocess case-lab-umd/llm-auditing-coin/6_discussion/LLM_predict.py official repository unverified MIT (permissive) · d586143500c563f6 · report
record_result case-lab-umd/llm-auditing-coin/6_discussion/LLM_predict.py official repository unverified MIT (permissive) · f76ceb3944d49dd6 · report
run_validation_on_preprocessed case-lab-umd/llm-auditing-coin/5_CoIn_pipline/main_learned_verify_efficient_acc.py official repository unverified MIT (permissive) · a23ed0eaf28abbcc · report
run_validation_on_preprocessed case-lab-umd/llm-auditing-coin/5_CoIn_pipline/main_learned_verify_efficient_other_metric.py official repository unverified MIT (permissive) · 3d239420db2c90e4 · report
run_validation_on_preprocessed_rule_based case-lab-umd/llm-auditing-coin/5_CoIn_pipline/main_rule_based_efficient_acc.py official repository unverified MIT (permissive) · 05c3140dd19ecd13 · report
verify_merkle_proof case-lab-umd/llm-auditing-coin/2_hash_tree/verify.py official repository unverified MIT (permissive) · 03c01d5adb6beae2 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections