Observed arrival · 2026-11-11
A workload calculator for LLM API bills
The page estimates monthly API costs across nine listed models using request volume, token counts, cache assumptions, and billing mode.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Teams estimating costs for LLM API workloads
- Worth noticing
- Batch mode excludes models without verified batch rates, and cache discounts are not combined with batch.
Field notes
The estimate is built from request volume and average input/output token counts, with optional cache-hit and baseline settings. Users can also change listed rates; the page says those overrides appear in the shareable link and are not stored on its side. Its rate table includes conditions such as DeepSeek peak periods and Qwen regional and long-input pricing, while the estimate excludes taxes, cache writes, storage, and tool fees.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
◎NicheUnusually specific use
One card from the complete issue