vitas/dsh-model-pricing
Compare LLM API prices before you pick a model and see what you actually paid after you used it — a pricing and capability table (~7,250 priced models, 213 providers) plus per-project spend and prompt-cache leak attribution read from your own session logs.
dsh-model-pricing compares LLM API prices before you pick a model and shows what you actually paid after you used it. It puts a pricing and capability table directly into DSH settings — input, output and cache-read price per 1M tokens, context window and max output across 213 providers and roughly 7,250 priced models — with capability tags computed from structured catalog fields (Coding, Agentic, Vision, Long context, Open weights, Structured output) and user-configurable rules. It then reads your own session logs through the same catalog: per-project spend priced by the route you actually called, prompt-cache leaks attributed by cause, and a price × speed quadrant measured from your own history.
Install
dsh plugin --profile web add dsh-model-pricingCopied verbatim from the README (the README also shows a local-checkout form dsh plugin --profile web add .).
Compatibility
A DSH Web profile plugin that renders in the DSH Settings page. It reads your own session logs and refreshes prices from public catalogs on your machine; for models DSH can actually invoke the harness's bundled pi-ai catalog overrides the public catalog, and divergences larger than 10% are flagged row by row.
Details
- Repo: vitas/dsh-model-pricing
- Category: Usage & Billing
- Stars: 2
- Version: GitHub repo vitas/dsh-model-pricing; npm package dsh-model-pricing at 0.6.1 (registry check 2026-10-09; registry repository field resolves back to this repo). Apache-2.0 license; listed on awesome-dsh-plugin.
Alternatives
Sttrevens/dsh-cost-meter · paolomandica/dsh-cost-usage-monitor · dongsheng123132/dsh-cost