The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Budgetary: estimate token spend listing page.
Budgetary tells you how many tokens an LLM query will cost — before you run it.
Budgetary is a hosted API at https://api.budgetary.tools that returns probabilistic pre-inference token-spend estimates for LLM queries. This repository holds the open-source clients that talk to it: language SDKs and editor plugins.
The SDK in this release is a stub — the call above illustrates the shape of the API surface, not a working implementation.
See docs/installation.md for per-client setup:
@budgetary/sdk on npmbudgetary on PyPIBearer-auth HTTP API at https://api.budgetary.tools. The wire contract is published at docs/api-contract.md.
Early access. The hosted API is live, but client interfaces may change between releases until they reach 1.0. Pin exact versions in production.
Apache-2.0. Copyright Budgetary.