# Torchcast Decision API

- [Torchcast Decision API](https://docs.torchcast.ai/index.md): Probabilities, not prose: ask yes/no, multiple-choice and ordinal questions about any text and get calibrated answers back.
- [Quickstart](https://docs.torchcast.ai/quickstart.md): Get an API key and make your first decision request.
- [Concepts](https://docs.torchcast.ai/concepts.md): State, questions, the three answer types, and how to read probabilities.
- [Models](https://docs.torchcast.ai/models.md): Pinned model ids, the latest alias, retirement, and the live model list.
- [Errors](https://docs.torchcast.ai/errors.md): Every error the API returns, and what your client should do.
- [Limits and rate limits](https://docs.torchcast.ai/limits.md): Request size limits, rate limits and their headers, timeouts, and retries.
- [Billing](https://docs.torchcast.ai/billing.md): Prepaid balance, billable tokens, adding credit, and credit expiry.
- [Migrating an existing decisions integration](https://docs.torchcast.ai/migrating.md): Move an existing decisions integration to Torchcast.
- [Privacy](https://docs.torchcast.ai/privacy.md): What happens to the content you send.
- [Changelog](https://docs.torchcast.ai/changelog.md): New models and API changes.
- [Create a decision](https://docs.torchcast.ai/api-reference/create-a-decision.md): Answers every question about `state` with probabilities. Each successful call is charged by its billable input tokens; a retried request is a new request and is charged again.
- [List models](https://docs.torchcast.ai/api-reference/list-models.md): Every model id with its status, effective limits and price. Public: no API key needed. Rate limited per client IP.

## OpenAPI Specs

- [openapi](/openapi.json)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.