Themata.AI
Themata.AI

Popular tags:

#developer-tools#ai-agents#discussion#trending#llms#ai-ethics#claude#code-generation#ai-safety#openai

AI is changing the world. Don't stay behind. Clear summaries, community insight, delivered without the noise. Subscribe to never miss a beat.

© 2026 Themata.AI • All Rights Reserved

Archive

|

Topics

|

Privacy

|

Cookies

|

Contact
← All stories

Story

Excessive token usage in Claude Code

1 report

1 website

1 discussion

Latest report

Overview

Claude Code version 2.1.1 exhibits excessive token usage, consuming tokens at a rate more than four times faster than previous versions. This issue has been reported specifically on Linux platforms.

Summary from github.com.

Reports

One report so far. Additional coverage will appear here when it is linked to this story.

  1. github.com

    Excessive token usage in Claude Code

    Read report →

Community reactions

Each reaction summarizes sampled comments from the linked discussion.

Hacker News · github.com

Excessive token usage in Claude Code ↗
Hacker News discussion ↗

Historical count: 5 · 5 saved in sample · Historical sample

Analysis ready

Read this discussion’s reaction

Based on 5 sampled comments from this thread. Analyzed 2026-02-21.

  • Praise: Professionals appreciate Claude's ability to spawn multiple subagents, as it enhances results despite higher token usage, indicating a strong preference for performance over cost.
  • Praise: Users of Opus 4.6 report stable usage numbers, suggesting that the model maintains consistent performance for agentic programming tasks.
  • Concern: The recent VS Code extension update has degraded user experience, causing agents to become unresponsive and breaking workflow, which highlights potential issues with reliability.
  • Concern: Many users express frustration over excessive token usage and limits, feeling that the model's behavior has become predatory, especially for those on lower-cost plans.
  • Concern: A user has completely stopped using Claude due to degraded quality and has found alternatives like Codex that better meet their needs, indicating a significant loss of trust.