Address
:
[go:
up one dir
,
main page
]
Include Form
Remove Scripts
Accept Cookies
Show Images
Show Referer
Rotate13
Base64
Strip Meta
Strip Title
Session Cookies
Skip to content
Navigation menu
Search
Powered by Algolia
Search
Log in
Create account
DEV Community
Close
#
cost
Follow
Hide
Posts
Left menu
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
Right menu
DataTransfer-Regional-Bytes: the AWS line that charges you for talking to yourself
Grain64
Grain64
Grain64
Follow
Nov 11
DataTransfer-Regional-Bytes: the AWS line that charges you for talking to yourself
#
aws
#
devops
#
cloud
#
cost
Comments
Add Comment
4 min read
Moderation
How much does a UX data lake help a small model on big screens? We measured completeness, rule by rule
MeloLabs.net
MeloLabs.net
MeloLabs.net
Follow
Nov 11
How much does a UX data lake help a small model on big screens? We measured completeness, rule by rule
#
haiku
#
ux
#
datalake
#
cost
Comments
Add Comment
12 min read
Moderation
Cache-read prices are where LLM bills quietly diverge: 50 models compared
尚毅段
尚毅段
尚毅段
Follow
Nov 11
Cache-read prices are where LLM bills quietly diverge: 50 models compared
#
ai
#
llm
#
api
#
cost
Comments
Add Comment
2 min read
Moderation
Give Haiku the project's memory, not the whole project
MeloLabs.net
MeloLabs.net
MeloLabs.net
Follow
Nov 10
Give Haiku the project's memory, not the whole project
#
rag
#
haiku
#
guide
#
cost
Comments
Add Comment
4 min read
Moderation
Your Free Lane Is Cheap Until Rework Tax Beats the Token Bill
Odd_Background_328
Odd_Background_328
Odd_Background_328
Follow
Nov 8
Your Free Lane Is Cheap Until Rework Tax Beats the Token Bill
#
devops
#
ai
#
observability
#
cost
Comments
1
 comment
5 min read
Moderation
Your AWS bill has two NAT Gateway lines. Here is how to read both.
Grain64
Grain64
Grain64
Follow
Nov 7
Your AWS bill has two NAT Gateway lines. Here is how to read both.
#
aws
#
devops
#
cloud
#
cost
Comments
1
 comment
4 min read
Moderation
Why Pay for the Smartest Model Every Time?
Konrad Wright
Konrad Wright
Konrad Wright
Follow
Nov 4
Why Pay for the Smartest Model Every Time?
#
machinelearning
#
inference
#
efficiency
#
cost
Comments
Add Comment
6 min read
Moderation
Spot vs Reserved GPUs: The Utilisation Number That Decides Everything
gxqwb
gxqwb
gxqwb
Follow
Nov 3
Spot vs Reserved GPUs: The Utilisation Number That Decides Everything
#
cloud
#
cost
#
ai
#
architecture
Comments
Add Comment
4 min read
Moderation
Should You Rent AI or Run Your Own?
Konrad Wright
Konrad Wright
Konrad Wright
Follow
Nov 2
Should You Rent AI or Run Your Own?
#
machinelearning
#
inference
#
cost
Comments
Add Comment
6 min read
Moderation
A reported $2.3 API bill doesn't tell you what the agent costs.
Dawncoral
Dawncoral
Dawncoral
Follow
Oct 31
A reported $2.3 API bill doesn't tell you what the agent costs.
#
ai
#
agents
#
cost
#
programming
1
 reaction
Comments
Add Comment
5 min read
Moderation
The managed Postgres bill nobody puts on the pricing page
Marc
Marc
Marc
Follow
Oct 30
The managed Postgres bill nobody puts on the pricing page
#
postgres
#
database
#
cost
#
selfhosting
Comments
Add Comment
3 min read
Moderation
AWS spot instances in production: a 2026 playbook
Abhishek Jaiswal
Abhishek Jaiswal
Abhishek Jaiswal
Follow
Oct 28
AWS spot instances in production: a 2026 playbook
#
aws
#
kubernetes
#
devops
#
cost
Comments
Add Comment
6 min read
Moderation
Free Workers Don't Ship Free Disk: Cap Artifact Retention First
Odd_Background_328
Odd_Background_328
Odd_Background_328
Follow
Oct 27
Free Workers Don't Ship Free Disk: Cap Artifact Retention First
#
devops
#
ai
#
cost
#
python
Comments
Add Comment
5 min read
Moderation
Ten reviews per LLM call cut the bill by 57%. A thousand per call only reaches 65%.
Andrey Altrouter
Andrey Altrouter
Andrey Altrouter
Follow
Oct 27
Ten reviews per LLM call cut the bill by 57%. A thousand per call only reaches 65%.
#
ai
#
llm
#
cost
#
beginners
1
 reaction
Comments
Add Comment
5 min read
Moderation
A cheap model that handles 70% of your requests can cut the bill by 65% — or raise it by 5%
Andrey Altrouter
Andrey Altrouter
Andrey Altrouter
Follow
Oct 26
A cheap model that handles 70% of your requests can cut the bill by 65% — or raise it by 5%
#
ai
#
llm
#
cost
#
beginners
Comments
Add Comment
5 min read
Moderation
👋
Sign in
for the ability to sort posts by
relevant
,
latest
, or
top
.
We're a place where coders share, stay up-to-date and grow their careers.
Log in
Create account