Forem

# costoptimization

Practical strategies and stories about reducing cloud infrastructure costs.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook

I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook

Comments
5 min read
Cut Your LLM Costs by 90% With Prompt Caching (And Why Most Developers Don't)

Cut Your LLM Costs by 90% With Prompt Caching (And Why Most Developers Don't)

Comments
4 min read
How a fintech startup cut cloud costs 65% with an open-source sovereign stack
Cover image for How a fintech startup cut cloud costs 65% with an open-source sovereign stack

How a fintech startup cut cloud costs 65% with an open-source sovereign stack

Comments
2 min read
Local LLMs vs Cloud APIs: Building Offline-First AI Workflows

Local LLMs vs Cloud APIs: Building Offline-First AI Workflows

Comments
8 min read
Kinesis Data Firehose Is Burning Our Budget: One Setting Changed Everything

Kinesis Data Firehose Is Burning Our Budget: One Setting Changed Everything

2
Comments
4 min read
How to Reduce LLM API Costs by 70% — 5 Strategies That Actually Work
Cover image for How to Reduce LLM API Costs by 70% — 5 Strategies That Actually Work

How to Reduce LLM API Costs by 70% — 5 Strategies That Actually Work

4
Comments
4 min read
Part 8 — Token-by-Token: Why AI Generates Text One Word at a Time (And Why It Costs 4x More)

Part 8 — Token-by-Token: Why AI Generates Text One Word at a Time (And Why It Costs 4x More)

Comments 1
9 min read
The Shadow Cloud Spend: $50k a Month FinOps Audit of Forgotten Dev Accounts

The Shadow Cloud Spend: $50k a Month FinOps Audit of Forgotten Dev Accounts

Comments
7 min read
They Don't Have the Money (And Neither Do You): The Coming Era of Small Models

They Don't Have the Money (And Neither Do You): The Coming Era of Small Models

Comments
6 min read
When Netlify killed my free tier: a 15-minute migration to Dokploy
Cover image for When Netlify killed my free tier: a 15-minute migration to Dokploy

When Netlify killed my free tier: a 15-minute migration to Dokploy

Comments
2 min read
AWS cost optimization: how we cut our bill by 60%
Cover image for AWS cost optimization: how we cut our bill by 60%

AWS cost optimization: how we cut our bill by 60%

Comments
6 min read
The History of Expanso (Part 4): The Mismatch

The History of Expanso (Part 4): The Mismatch

Comments
3 min read
How a SaaS platform cut infrastructure costs by 40% while improving response times
Cover image for How a SaaS platform cut infrastructure costs by 40% while improving response times

How a SaaS platform cut infrastructure costs by 40% while improving response times

Comments
3 min read
How to Add Old Models to Claude Code /model Picker: 3 Methods Tested

How to Add Old Models to Claude Code /model Picker: 3 Methods Tested

Comments
5 min read
I Audited 3 Months of Claude Code Billing — Most Community Cost-Saving Tips Don''t Work

I Audited 3 Months of Claude Code Billing — Most Community Cost-Saving Tips Don''t Work

Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.