Practical guides
Start here when the question is a bill, a migration, or a script, not a headline.
Tools
-
AI API cost calculator
Price a workload from token counts. Runs the same formula as the guide, in the browser.
-
Cron builder and explainer for pipelines
Explain a cron expression, check the next runs in a real timezone, and get the day-of-month trap spelled out.
-
Epoch and timestamp converter for pipelines
Turn epoch numbers into ISO, SQL and pandas output. Detects the unit from the digit count and runs entirely in the browser.
-
Long-context surcharge calculator
One token over the threshold reprices the entire request. See the cliff, and what the naive calculation leaves out.
-
MCP server config generator and validator
Generate an MCP server config for six clients, or paste the one that is not working and find out which line broke it.
-
PII redaction tester
Paste the text you are about to send a model and redact structured identifiers in the browser. Checksum checks separate a real card from a lookalike.
-
Prompt cache break-even calculator
Caching has a write premium at Anthropic, so it loses money below a 21.7 percent hit rate. Check your own numbers.
-
RAG index cost calculator
Cost a RAG index before you build it: embedding the corpus, overlap inflation, and the per-query bill at your traffic.
-
Snowflake warehouse credit and resize calculator
What a Snowflake warehouse really costs per day, floor charges and all, and the speedup that justifies moving up a size.
-
Token and context budget calculator
Estimate a prompt's tokens, compare the Claude tokenizer penalty against OpenAI's, and check the request fits the window.
-
Tool schema builder for strict mode
Infer a schema from sample JSON, get the strict-mode version that stops the API rejecting it, and validate one that already failed.
Guides
-
Batch is half price. The wait is the cost
Batch cuts GPT-6.1 Sol from $10 to $5 per million output tokens. On a 2 million token nightly run that is $220 a month, if the job can wait.
-
Count the tokens, then price the call
A short Python script prices an API call from a real trace: 8,000 in and 1,500 out is $0.031 on Sol and $0.155 on Astra.
-
How to estimate an AI API bill before you ship
Two million output tokens a day costs $20 on GPT-6.1 Sol and $100 on Astra. Here is the arithmetic, from list price to a monthly bill.
-
Docker container vs virtual machine: what changes
A Docker container vs virtual machine comparison: containers share the host kernel and run isolated processes in megabytes, while VMs virtualize hardware and carry a full OS in gigabytes. The right base image and layer order cut a 2 GB image to under 100 MB.
-
How to shrink a Docker image without breaking it
Reduce Docker image size by choosing slim bases and multi-stage builds. A 2.54 GB image can drop under 200 MB, cutting pull time and storage cost tenfold.
-
How to write a Dockerfile that does not waste your time
To write a Dockerfile that builds fast, order instructions from least to most frequently changing. Copy dependency files before source code so Docker reuses cached layers. Reordering two lines cut rebuild time 81 percent, from 37.4 to 7.1 seconds.