Choose
Compare model profiles and editable per-million-token rates.
Compare models, plan shared AI credits, and see what every request costs. A practical workspace for communities building with AI.
Select two model profiles, enter a prompt, and compare estimated cost. Run a local prompt analysis or connect a private LiteLLM-compatible gateway for actual model output.
Analysis is deterministic and runs in your browser. Estimates are based on editable reference rates.
From model choice to allocation, each visible number follows a rule you can inspect.
Compare model profiles and editable per-million-token rates.
Divide a local demo budget across members without exceeding the pool.
Analyze a prompt, record an illustrative charge, and export your ledger.
Bring your own LiteLLM-compatible gateway for actual response comparison.
Try an allocation locally. Changes persist in this browser. Shared enforcement, wallet membership, and on-chain settlement require future services.
This ledger contains only activity from this browser. Demo analysis is estimated; gateway rows report model usage when returned, with cost still estimated from your rates.
| TIME | MEMBER | MODE | MODEL | TOKENS | EST. USD |
|---|---|---|---|---|---|
| No events yet. Run a prompt analysis to begin a local record. | |||||
Quota Loom makes model choice and credit rules tangible. A production community pool needs identity, a secure gateway, persistent accounting, and enforceable limits.