# spinf

> spinf (speedy inference) answers many questions about a piece of content in a single pass: each question is a short plain-language statement, and spinf returns the probability that it holds. Only input tokens (content + queries) are billed, at $0.07 per million tokens; the scores are free. Beta.

## Docs

- [Overview](https://spinf.com/docs/index.md)
- [Quickstart](https://spinf.com/docs/quickstart.md)
- [Scoring API (draft)](https://spinf.com/docs/scoring-api.md)
- [Calibration](https://spinf.com/docs/calibration.md)
- [Limits & pricing](https://spinf.com/docs/limits.md)