Costtracking

👋 Sign in for the ability to sort posts by relevant, latest, or top.

John Medina

Jun 22

How to Stop One Customer From Blowing Up Your Entire LLM Budget

#llm #opensource #ai #costtracking

2 min read

John Medina

Jun 15

Over-editing is a token tax: GPT-5.4 ships 6.5x more diff per fix than Claude Opus 4.6, and your bill notices

#llm #opensource #ai #costtracking

2 min read

John Medina

Jun 5

Stop Paying for Failed AI Agent Retries

#llm #opensource #ai #costtracking

1 min read

John Medina

Jun 3

Over-editing is a token tax: GPT-5.4 ships 6.5x more diff per fix than Claude Opus 4.6, and your bill notices

#llm #opensource #ai #costtracking

2 min read

John Medina

Jun 1

Stop sharing one OpenAI key across all your users

#llm #opensource #ai #costtracking

1 min read

John Medina

May 25

The Token Spiral: How One Runaway AI Agent Burned $2,847 in 4 Hours

#llm #opensource #ai #costtracking

2 min read

John Medina

May 22

The Token Spiral: How One Runaway AI Agent Burned $2,847 in 4 Hours

#llm #opensource #ai #costtracking

2 min read

John Medina

May 18

Your AI costs are growing faster than your revenue

#llm #opensource #ai #costtracking

1 min read

John Medina

May 20

The Overlooked Costs of Your LLM API Calls

#llm #opensource #ai #costtracking

2 min read

John Medina

May 15

How I track per-customer LLM costs in production

#llm #opensource #ai #costtracking

2 min read

John Medina

May 27

You Don't Need Enterprise LLMOps, You Need a Better Dashboard

#llm #opensource #ai #costtracking

2 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

# costtracking

How to Stop One Customer From Blowing Up Your Entire LLM Budget

Over-editing is a token tax: GPT-5.4 ships 6.5x more diff per fix than Claude Opus 4.6, and your bill notices

Stop Paying for Failed AI Agent Retries

Over-editing is a token tax: GPT-5.4 ships 6.5x more diff per fix than Claude Opus 4.6, and your bill notices

Stop sharing one OpenAI key across all your users

The Token Spiral: How One Runaway AI Agent Burned $2,847 in 4 Hours

The Token Spiral: How One Runaway AI Agent Burned $2,847 in 4 Hours

Your AI costs are growing faster than your revenue

The Overlooked Costs of Your LLM API Calls

How I track per-customer LLM costs in production

You Don't Need Enterprise LLMOps, You Need a Better Dashboard