Oleksandr Kuzmenko, EditorPublished 5 min readAI-assisted · editor-reviewed
TL;DR
- Agentic coding tools make an average of 12 model calls and process 2.9 million tokens per user prompt.
- Prompt-cache re-reads account for 96% of all processed tokens in multi-step agent workflows.
- Agentic AI tasks consume around 150 Wh per prompt, roughly 600 times more energy than standard chatbot prompts.
Key facts
- Tokens Processed (8 weeks)
- 3.2 Billion
- Average Calls per Prompt
- 12 model invocations
- Cache Reads Share
- 96% of total tokens
- Model Output Share
- 0.4% of total tokens
Source: Key facts — Tokens Processed (8 weeks)
Source: Key facts. Tokens Processed (8 weeks): 3.2 Billion. Each figure is copied from the story.
- Tokens Processed (8 weeks)3.2 Billion
Source: Key facts — Cache Reads Share, Model Output Share
Source: Key facts. Cache Reads Share: 96% of total tokens. Model Output Share: 0.4% of total tokens. The chart compares only values that share a unit. Each figure is copied from the story.
Metric chart
- 96% of total tokensCache Reads Share
- 0.4% of total tokensModel Output Share
- Cache Reads Share96% of total tokens
- Model Output Share0.4% of total tokens
The Token Breakdown of Agentic Workflows
Empirical data collected over 8 weeks of intensive Claude Code usage highlights the stark difference between standard LLM chat prompts and agentic tool loops:
- Total Prompts: 1,138 human inputs
- Model Calls: 14,000+ total invocations (~12 calls per user prompt)
- Token Volume: 3.2 billion tokens processed (~2.9M tokens per prompt)
- Output Share: Model generated output represents only 0.4% of total tokens
- Cache Read Share: Context re-reads account for 96% of token volume
Energy and Compute Scale
Standard single-turn LLM chat queries consume approximately 0.24–0.34 Wh per prompt. In contrast, an agentic coding prompt averages 150 Wh (range 60–290 Wh), representing a ~600x increase in computational energy due to context window re-evaluations on every step.
Disparity Between Benchmarks and Real Usage
Published per-query metrics evaluate single text interactions, but modern coding agents engage in complex multi-step reasoning chains. Research by Watershed (Bistline et al. 2026) confirms that agentic workflows consuming 5–50 model calls require 50–500 Wh per task, while 97% of Anthropic API traffic now exhibits automation-dominant patterns.
What to do today
- Account for multi-step model calls when estimating the environmental and financial costs of autonomous coding agents.
- Monitor context window accumulation in agentic workflows to track token volume escalation.
Step names are taken from What to do today.
Step names are taken from What to do today. Account for multi-step model calls when estimating the environmental and financial costs of autonomous coding agents.. Monitor context window accumulation in agentic workflows to track token volume escalation.
- Account for multi-step model calls when estimating the environmental and financial costs of autonomous coding agents.
- Monitor context window accumulation in agentic workflows to track token volume escalation.