#cost
23 posts
-
AI Code Rework Cost: When You Pay Twice for the Same Lines
Code that lands and then gets rewritten was paid for twice, once to write it and once to remove it. How to measure rework from git alone, what a 50% threshold and a 14-day window actually catch, and why the figure is measured spend rather than a saving.
-
AI Commit Attribution: How Accurate Is the Cost on a Pull Request?
Any tool can print a dollar figure against a PR. The number can rest on the agent's own git commit call or on a same-day guess, and most dashboards render both identically. How to tell which you have.
-
Cursor OpenTelemetry Export: What Ships Today, and What You Get Without Enterprise
Cursor now streams OTLP metrics and logs to a collector you run. The exact wire, the six things it will not send, and what the other plans can actually export.
-
Agent Session Cost: What the Sessions That Left No Commit Cost You
Cost per merged PR divides agent spend by the work that landed, so the sessions that landed nothing vanish into the average. How to measure that spend, and why it is not a saving.
-
Model Downsizing: How to Run Cheap Agent Work on Cheap Models
Model downsizing runs mechanical agent turns on a cheaper model. How to spot downsizing candidates in your own usage and cut agent cost without guessing.
-
Prompt Caching Read vs Write: When Caching Costs More Than It Saves
A cache read is cheap, a cache write costs a premium. The break-even math, the net-negative case, and the write:read ratio that tells you which one you're in.
-
Some of Your Agent's Tasks Don't Need an Agent
Parts of your agent run the same deterministic tool-call sequence on every run, and you pay model tokens each time to reproduce what a plain script would do for free.
-
Stop Paying to Re-Plan Work Your Agent Already Solved
Agents re-derive the same plan skeleton on every run. TokenJam clusters your runs by plan shape, isolates the planning tokens, and exports the repeated plans as templates you can feed back in.
-
Stop Paying Frontier-Model Prices for Work a Cheaper Model Handles
Find the agent calls where a cheaper model would likely hold, priced in dollars against your own trace history, so you stop paying frontier rates for mechanical work.
-
Instrument Your AI Agent, Then Find Where the Money Goes
Patch your provider client in one line so the TokenJam SDK captures every LLM call to a local, on-disk trace, then run local analyzers that turn those traces into priced savings across your self-built agent.
-
Half Your System Prompt Isn't Doing Any Work
System prompts quietly accumulate dead-weight tokens you re-pay on every call, and TokenJam's Trim lever scores which tokens carry little significance so you can see what to cut.
-
The Prompt-Caching Discount Most Agents Leave on the Table
Prompt caching gives roughly 30-60% off the repeated prefix tokens your agent re-sends every call, and TokenJam measures your current cache usage and recommends where to place cache_control.
-
Why Model Autorouting Savings Need a Proof Step
Model autorouting to a cheaper, smaller, or open-source model shows a big savings number before any work is redone. That figure is a prediction of your AI spend, not a result. Here's why LLM cost savings from an autorouted swap stay a hypothesis until you replay it on your own tasks and measure whether quality holds or regresses.
-
What Actually Costs Money in an Agent Loop
A mechanism-level breakdown of where tokens get spent every turn an agent runs: input, output, cache reads vs cache writes, context bloat, tool overhead, fan-out, and retries.
-
Quota, Not Cost: Why /cost Is the Wrong Number on Claude Max
Claude Pro and Max subscribers should track quota, their usage against the plan window, not dollar cost, and /cost misleads them because it prices tokens against an API rate card they never pay.
-
Where Does Your Claude Code Quota Actually Go?
TokenJam is a local-first tool that reads your on-disk Claude Code transcripts and shows where a Pro or Max subscription's quota is spent per turn: re-reading context versus doing real work.
-
Introducing TokenJam Bench: Benchmarks & Evaluations for Agents and LLMs
TokenJam Bench is an open-source tool to benchmark and evaluate LLMs and agents. Run a candidate model against an original on real, executable task suites and get a measured pass-rate, confidence intervals, and a holds-or-regressed verdict. Local, no signup.
-
The problem with TokenMaxxing
TokenMaxxing is fun because someone else pays for it. Here's why the subsidy is ending, what Fable 5 just signaled, and how to find your own multiple.
-
What is an agent loop?
Agent loops: the program that prompts your agent for you, checks its own work, and decides when to stop. The lineage from ReAct to orchestration, and why the loop is now the expensive part.
-
Cost dashboards tell you the bill. They don't tell you what to change.
The gap between reporting agent cost and recommending what to do about it. Why an honest recommendation needs to be validated against the user's own data, and the recent research that makes that validation cheap.
-
Where Your AI Agent Bill Goes: 5 Token Waste Patterns
Model overspending, context bloat, redundant calls, runaway loops, and poor caching. What each one does to the bill, and the published technique that cuts it.
-
AI Agent Costs Are Real Now: What the 2026 Numbers Show
Uber burned a year of AI budget in four months. The sourced 2026 agent-spend figures, what the $1.3M bill is at standard pricing, and the June billing changes.
-
What is AI Agent Token Economics?
Agent token economics: understanding where tokens are spent, why agent costs spike unpredictably, and the optimization patterns (model cascading, prompt compression, semantic caching) for reducing spend without losing quality.