Skip to main content

worthune

Zero-dependency SDK for the Worthune Model API — verified financial calculation models you can cite, audit, and trust. No API keys. Free with attribution.

Every model has a published spec, an independent second implementation that must agree with the first on 250 fuzzed cases before anything ships, and IRS/SSA constants traced to primary sources. Model changes are never silent: responses pin specVersion, and the changelog is public.

pip install worthune
from worthune import Worthune, verify_record

client = Worthune()

result = client.run("relocation", {
    "currentSalary": 95000, "newSalary": 108000,
    "currentMonthlyExpenses": 4200, "newMonthlyExpenses": 4900,
    "movingCosts": 6000, "currentSavings": 40000,
    "annualReturn": 0.07, "yearsHorizon": 10,
})

result["outputs"]["breakEvenMonths"]  # 16
result["specVersion"]                 # pinned contract version
result["facts"]                       # IRS/SSA constants used, with sources
result["sentinels"]                   # special values, explained
verify_record(result)                 # True — audit fingerprint checks out

API

  • client.list_models() — catalog with spec versions
  • client.get_contract(model) — machine-readable inputs/domains/sentinels
  • client.get_spec(model) — the full published spec (markdown)
  • client.run(model, inputs) — run; validation failures return {"ok": False, "errors": [...]} instead of raising
  • client.get_eval_dataset(model) — 250 verified input/expected-output pairs, the exact cases Worthune's dual-implementation CI verifies (ground truth for financial AI testing)
  • client.get_facts() — the sourced IRS/SSA constants registry
  • verify_record(response) — recompute the SHA-256 decision record to prove where numbers came from (byte-exact ECMAScript-compatible canonical JSON)

Retirement, FIRE, rent vs. buy, loans and credit, retirement tax (RMDs, Roth ladders, capital gains), and startup finance (SAFE dilution, burn rate, SBA loan cost) — the catalog grows in verified packs; client.list_models() or the live catalog is always current.

Fair use: 5,000 runs/month per app (a guideline, not a meter) — the free tier, in writing.

MIT licensed. The models, specs, and verification harness live behind the API at worthune.com.

Metadata

Release files for worthune 0.1.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for worthune 0.1.1
File Size Uploaded Provenance Actions
worthune-0.1.1.tar.gz 6.7 kB Without provenance Details for worthune-0.1.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for worthune 0.1.1
File Interpreter ABI Platform Actions
worthune-0.1.1-py3-none-any.whl Python 3 none any Details for worthune-0.1.1-py3-none-any.whl

Total release size: 12.3 kB

Release files / worthune-0.1.1.tar.gz

Download URL worthune-0.1.1.tar.gz
Size 6.7 kB
Tags Source
SHA-256 checksum
How to use checksums
4385523d1ff0cec78fd11393da8f3901ad863f180065e2c90365455434a34613
BLAKE2b-256 checksum
How to use checksums
4bbccb48d3962ece8a954d3361eaa9f41d64bf6619da90c1ad06e210683672f2
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Release files / worthune-0.1.1-py3-none-any.whl

Download URL worthune-0.1.1-py3-none-any.whl
Size 5.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
98b1db40b83044233a291553b565605cda8298cf46559e8dbd11d16e6e7f9554
BLAKE2b-256 checksum
How to use checksums
363071bcf01af352eb6c65b620090d534914e39257410e07d744ad3fa0261103
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.14

Security for worthune 0.1.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page