LiteLLM
by BerriAI
Open-source LLM gateway and SDK that tracks spend per key, team and model, with proxy API endpoints for spend logs.
- Category
- Cloud & Data Platforms
- Type
- LLM observability
- Interface
- REST API
- Built with
- Connect Any API
- Credentials
- Access token
- Docs
- LiteLLM API docs
02Data
What you can sync.
- Spend logs
- Keys
- Teams
- Model usage
Load LiteLLM spend logs into your Lake and model it in the Warehouse with the rest of your stack.
Need more? Name any other LiteLLM data the API returns, and the AI adds it to the connector.
03Credentials
Credentials you will need.
- An access token
LiteLLM uses an access token. You add the credentials once, when the AI asks for them, and it tells you where to create them in BerriAI if you need help.
04How it works
How it works in DataMind.
-
Pick LiteLLM.
Open Lake, pick LiteLLM in the source picker and name the connection. Connect Any API opens with a ready prompt that points the AI at the LiteLLM API docs.
-
Answer a few questions.
The AI reads the LiteLLM documentation, then asks which credentials you will use, which data to sync (for example spend logs and keys), whether you want a one-time load or a recurring sync, and which accounts or filters apply.
-
Your data lands in Lake.
It builds the connector, tests it and shows you sample rows. Then LiteLLM data loads into your Lake on your schedule, ready for the Warehouse, DataPrism BI and AI Minds.
