---
title: "LLMs: Reference"
description: "Provider-agnostic LLM configuration reference for CrewAI projects."
icon: "book"
mode: "wide"
---

## Common parameters

- `model`
- `temperature`
- `max_tokens`
- `timeout`
- `max_retries`
- `response_format`

## Contract guidance

- Set low temperature for extraction/classification.
- Use structured outputs for downstream automation.
- Set explicit timeout and retry policy for production.

## Canonical source

Primary API details live in [/en/concepts/llms](/en/concepts/llms).