Skip to main content

Python

Minimal install

Core dependencies: pydantic>=2.0.0, httpx>=0.25.0, tiktoken>=0.5.0, rich>=13.0.0.

With providers

Individual providers:

With framework integrations

Local inference

Ollama does not need a Python package — cascadeflow communicates with Ollama via HTTP at localhost:11434. Install Ollama separately from ollama.ai.

Everything

Development

TypeScript

Core

Framework packages

Provider Setup

Set API keys as environment variables:
cascadeflow auto-detects available providers based on which API keys are set.

Verify Installation

Next Step

Start observing your LLM calls with zero code changes. Quickstart: Observe Mode →