---
title: "Weights & Biases"
url: "/docs/observability/wandb_integration"
canonical_url: "https://docs.litellm.ai/docs/observability/wandb_integration"
type: "docs"
last_updated: "2026-10-03"
summary: "This is community maintained, Please make an issue if you run into a bug"
related:
  - "/docs/observability/qualifire_integration"
  - "/docs/observability/azure_sentinel"
---
# Weights & Biases

> Index of all LiteLLM docs: https://docs.litellm.ai/llms.txt


:::tip

This is community maintained, Please make an issue if you run into a bug
https://github.com/BerriAI/litellm

:::

Weights & Biases helps AI developers build better models faster https://wandb.ai

:::info
We want to learn how we can make the callbacks better! Meet the LiteLLM [founders](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version) or
join our [discord](https://discord.gg/wuPM9dRgDw)
::: 

## Pre-Requisites
Ensure you have run `uv add wandb` for this integration
```shell
uv add wandb litellm
```

## Quick Start
Use just 2 lines of code, to instantly log your responses **across all providers** with Weights & Biases

```python
litellm.success_callback = ["wandb"]
```
```python
# uv add wandb 
import litellm
import os

os.environ["WANDB_API_KEY"] = ""
# LLM API Keys
os.environ['OPENAI_API_KEY']=""

# set wandb as a callback, litellm will send the data to Weights & Biases
litellm.success_callback = ["wandb"] 
 
# openai call
response = litellm.completion(
  model="gpt-5.6-luna",
  messages=[
    {"role": "user", "content": "Hi 👋 - i'm openai"}
  ]
)
```

## Support & Talk to Founders

- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

## Related pages

- [Qualifire](https://docs.litellm.ai/docs/observability/qualifire_integration.md)
- [Azure Sentinel](https://docs.litellm.ai/docs/observability/azure_sentinel.md)