[go: up one dir, main page]

DEV Community

#cost

Posts

👋 Sign in for the ability to sort posts by relevant, latest, or top.
DataTransfer-Regional-Bytes: the AWS line that charges you for talking to yourself

DataTransfer-Regional-Bytes: the AWS line that charges you for talking to yourself

Comments
4 min read
How much does a UX data lake help a small model on big screens? We measured completeness, rule by rule

How much does a UX data lake help a small model on big screens? We measured completeness, rule by rule

Comments
12 min read
Cache-read prices are where LLM bills quietly diverge: 50 models compared

Cache-read prices are where LLM bills quietly diverge: 50 models compared

Comments
2 min read
Give Haiku the project's memory, not the whole project

Give Haiku the project's memory, not the whole project

Comments
4 min read
Your Free Lane Is Cheap Until Rework Tax Beats the Token Bill

Your Free Lane Is Cheap Until Rework Tax Beats the Token Bill

Comments 1
5 min read
Your AWS bill has two NAT Gateway lines. Here is how to read both.

Your AWS bill has two NAT Gateway lines. Here is how to read both.

Comments 1
4 min read
Why Pay for the Smartest Model Every Time?

Why Pay for the Smartest Model Every Time?

Comments
6 min read
Spot vs Reserved GPUs: The Utilisation Number That Decides Everything

Spot vs Reserved GPUs: The Utilisation Number That Decides Everything

Comments
4 min read
Should You Rent AI or Run Your Own?

Should You Rent AI or Run Your Own?

Comments
6 min read
A reported $2.3 API bill doesn't tell you what the agent costs.

A reported $2.3 API bill doesn't tell you what the agent costs.

1
Comments
5 min read
The managed Postgres bill nobody puts on the pricing page

The managed Postgres bill nobody puts on the pricing page

Comments
3 min read
AWS spot instances in production: a 2026 playbook

AWS spot instances in production: a 2026 playbook

Comments
6 min read
Free Workers Don't Ship Free Disk: Cap Artifact Retention First

Free Workers Don't Ship Free Disk: Cap Artifact Retention First

Comments
5 min read
Ten reviews per LLM call cut the bill by 57%. A thousand per call only reaches 65%.

Ten reviews per LLM call cut the bill by 57%. A thousand per call only reaches 65%.

1
Comments
5 min read
A cheap model that handles 70% of your requests can cut the bill by 65% — or raise it by 5%

A cheap model that handles 70% of your requests can cut the bill by 65% — or raise it by 5%

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