# Guidance

Python library that interleaves generation and control flow while constraining language-model output.

- Company: Guidance contributors
- Category: Platforms & Infrastructure
- Business model: Open (open weights/source)
- Availability: unknown
- Launched: Not recorded
- Tags: struct, developer-tools
- Website: https://guidance.readthedocs.io/
- Documentation: https://github.com/guidance-ai/guidance
- Pricing page: Not recorded
- License: Not recorded
- Canonical URL: https://globalaiproductindex.com/products/guidance/
- Record updated: 2026-11-03

Typical uses include Schema-constrained data extraction; Validation of generated application data. Documented capabilities: Constrain generation with regex and context-free grammars; Mix loops, conditionals and model generation; Backends including Transformers, llama.cpp and OpenAI.

## Key features

- Constrain generation with regex and context-free grammars
- Mix loops, conditionals and model generation
- Backends including Transformers, llama.cpp and OpenAI

## Use cases

- Schema-constrained data extraction
- Validation of generated application data

## Pricing

The open-source software can be run on your own infrastructure. Compute, storage and any external model API usage are separate costs; a managed service is not included.

## FAQ

**Where does Guidance fit in a workflow?**

Python library that interleaves generation and control flow while constraining language-model output. Constrain generation with regex and context-free grammars.

**What costs and limits should I compare before choosing Guidance?**

The open-source software can be run on your own infrastructure. Compute, storage and any external model API usage are separate costs; a managed service is not included.

## Sources

- [Guidance — official product](https://guidance.readthedocs.io/)
- [Guidance — official documentation and terms](https://github.com/guidance-ai/guidance)

---
Data from the [Global AI Product Index](https://globalaiproductindex.com/), licensed CC BY 4.0.