Tech News
← Home  ·  All topics

Token Usage

3 GoKawiil briefs on this topic · RSS for token usage

Claude Code's background status-line summaries found consuming up to 20% of token spend

A community audit using Claude Code's own OpenTelemetry data found that the tool repeatedly sends each background agent's full transcript to its model (usually Opus) every ~30 seconds, asking for a 3-5 word summary of its last action, solely to update a status line. Flamerix AI's analysis found this 'agent_summary' traffic accounted for roughly 16-20% of API requests and spend, more than the main conversation itself, with no built-in setting to disable it since it became default in version 2.1.232. The developer released a Bun preload script, no-agent-summary.js, that intercepts and suppresses these summary calls without modifying the Claude Code binary.

Blog post argues developers should self-host LLM proxies for visibility

A developer-focused blog post contends that relying on an AI provider's built-in analytics dashboard gives users little real insight into token usage or request behavior. Instead, the author recommends running a self-hosted LLM proxy that logs which API key called which model, from which client, and when, across multiple providers and models from one endpoint.

OpenRouter data shows AI agents now consuming 5x more tokens than humans

Futurum Group CEO Daniel Newman cited an Andreessen Horowitz chart of OpenRouter data showing AI agents used 7.3 trillion tokens versus 1.4 trillion for humans as of August, six months after agent usage overtook human usage. OpenRouter says over 85% of agent tokens come from cached prompts, and since February agent token usage has risen 14x compared with 2.8x growth in human usage.