[2604.22750] How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks

-->

Computer Science > Computation and Language

arXiv:2604.22750 (cs)

[Submitted on 24 Apr 2026 (v1), last revised 29 Apr 2026 (this version, v2)]

Title:How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks

Authors:Longju Bai, Zhemin Huang, Xingyao Wang, Jiao Sun, Rada Mihalcea, Erik Brynjolfsson, Alex Pentland, Jiaxin Pei<br>View a PDF of the paper titled How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks, by Longju Bai and 7 other authors

View PDF

Abstract:The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a significant amount of tokens, three questions naturally arise: (1) Where do AI agents spend the tokens? (2) Which models are more token-efficient? and (3) Can agents predict their token usage before task execution? In this paper, we present the first systematic study of token consumption patterns in agentic coding tasks. We analyze trajectories from eight frontier LLMs on SWE-bench Verified and evaluate models' ability to predict their own token costs before task execution. We find that: (1) agentic tasks are uniquely expensive, consuming 1000x more tokens than code reasoning and code chat, with input tokens rather than output tokens driving the overall cost; (2) token usage is highly variable and inherently stochastic: runs on the same task can differ by up to 30x in total tokens, and higher token usage does not translate into higher accuracy; instead, accuracy often peaks at intermediate cost and saturates at higher costs; (3) models vary substantially in token efficiency: on the same tasks, Kimi-K2 and Claude-Sonnet-4.5, on average, consume over 1.5 million more tokens than GPT-5; (4) task difficulty rated by human experts only weakly aligns with actual token costs, revealing a fundamental gap between human-perceived complexity and the computational effort agents actually expend; and (5) frontier models fail to accurately predict their own token usage (with weak-to-moderate correlations, up to 0.39) and systematically underestimate real token costs. Our study offers new insights into the economics of AI agents and can inspire future research in this direction.

Subjects:

Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC); Software Engineering (cs.SE)

Cite as:<br>arXiv:2604.22750 [cs.CL]

(or<br>arXiv:2604.22750v2 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2604.22750

Focus to learn more

arXiv-issued DOI via DataCite

Submission history<br>From: Jiaxin Pei [view email]<br>[v1]<br>Fri, 24 Apr 2026 17:54:47 UTC (933 KB)

[v2]<br>Wed, 29 Apr 2026 17:20:11 UTC (931 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled How Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks, by Longju Bai and 7 other authors<br>View PDF<br>TeX Source

view license

Current browse context:

cs.CL

next >

new<br>recent<br>| 2026-04

Change to browse by:

cs<br>cs.AI<br>cs.CY<br>cs.HC<br>cs.SE

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for...