AI Coding AssistantsClaude Code High Token Usage: Where the Bill Comes From
Across 20,285 billed turns the operator typed 47,296 tokens and the input side came to 4.25 billion. Shorter prompts move a rounding error.
Aug 2812 min read
CATEGORY · 47 ARTICLES
AI Coding Assistants
Articles
AI Coding Assistants
AI Coding AssistantsHow to Speed Up Claude Code: 270 Turns, Timed
A median turn takes 3m 08s and 44 steps to get there. The lever is the number of steps, not the size of the context.
Aug 2812 min read
AI Coding AssistantsClaude Code Slow After Update: We Measured 17 Versions
Every assistant turn stamps its own version and its own token count, so the question is answerable retroactively. Across 17 versions the cost per turn fell 47% from its peak.
Aug 2712 min read
AI Coding AssistantsWhat Model Does Claude Code Use? Measured, Not Documented
One five-word prompt billed two different models. The resolution chain that picks them ends somewhere your repository cannot see, and the script that proves it.
Aug 1511 min read
AI Coding AssistantsMCP Server Setup with Claude Code: The Complete Guide
Claude Code's own toolset costs 122,137 bytes as an MCP server. That number is the budget every server you install is competing against, and nothing surfaces it.
Aug 916 min read
AI Coding AssistantsMultiple MCP Servers in One Client: Configuration Guide
Five servers start concurrently in under three seconds. The bill that actually matters is 30,218 bytes of tool definitions sitting in context on every single message.
Aug 912 min read
AI Coding AssistantsBest MCP Servers for Developers
Tool counts, cold and warm startup, and the context each server spends before doing anything — plus the two servers every list recommends that npm returns 404 for.
Aug 812 min read
AI Coding Assistantsmcp.json Configuration Explained
The three scopes, every field that does something, and the unset-variable trap that passes the literal string ${VAR} to your server instead of failing.
Aug 811 min read