---
slug: "instructor"
name: "Instructor"
effect: "Returns validated Pydantic objects from LLM calls, retrying automatically when validation fails"
category: "model-api"
url: "https://python.useinstructor.com/"
github: "567-labs/instructor"
pricing: "open-source"
license: "MIT"
tags: ["structured-outputs", "pydantic", "python", "validation", "extraction"]
platforms: []
install_kind: "pip"
date_added: "2026-10-14"
drop_score: 36
stars: 14014
pushed_at: "2026-10-14T22:21:57Z"
signals_status: "ok"
signals_fetched_at: "2026-10-15T01:18:59.246Z"
page: "https://agenttooldrop.com/tools/instructor"
---

# Instructor

Returns validated Pydantic objects from LLM calls, retrying automatically when validation fails

Category: Models and APIs. Pricing: Open source. License: MIT.

## Why you would want it

Instructor lets you pass a Pydantic model as `response_model` and get back a typed, validated object instead of parsing JSON or tool calls yourself. `instructor.from_provider` uses the same API for OpenAI, Anthropic, Google, Ollama, Groq and other providers. Failed validations are retried with the error message, partial objects can be streamed as they are generated, and nested models work without extra code. Ports exist for TypeScript, Ruby, Go and Elixir.

## Best for

- Structured extraction from text
- Pydantic-based Python apps
- Typed outputs across providers

## Use it when

You need reliable structured data from an LLM call and want validation and retries handled for you.

## Skip it if

You need full agent runs, built-in observability or shareable traces; the Instructor README itself points to PydanticAI for that.

## Install

Install with pip:

```sh
pip install instructor
```

Source: https://github.com/567-labs/instructor#readme

## Live signals

Fetched 2026-10-15T01:18:59.246Z (status: ok).

- Repository: 567-labs/instructor
- Stars: 14,014
- Forks: 1,307
- Open issues and PRs: 189
- License (GitHub): MIT
- Last push: 2026-10-14
- Latest release: v1.17.0 (2026-09-09)

## Links

- Website: https://python.useinstructor.com/
- GitHub: https://github.com/567-labs/instructor
- Install instructions verified at: https://github.com/567-labs/instructor#readme
- Source for this entry: https://github.com/567-labs/instructor#readme
- AgentToolDrop page: https://agenttooldrop.com/tools/instructor
- Full catalog (JSON): https://agenttooldrop.com/tools.json