apples and API pricings

You can use the models I mentioned directly from DeepSeek, Meta and Xiaomi and not exceed $40. Were it not for GLM 5.3 blowing up a quarter of my monthly budget in 5h, we are actually looking at something like $30.

$0.50 for cache reads, which is 25% of input. While other models are 10% of input.

And like that grok4.7 cache reads are more expensive than sol's (at $0.40/mil).

an actual tool https://github.com/gastownhall/beads

don't expect it to be opus, but luna does coding just fine for its size/price

claude code VSS - 70Gb

codex VSS - 600Mb