Documentation
🚅 LiteLLM + Groq for Production Deployments
LiteLLM provides a simple framework with features to help productionize your application infrastructure, including:
- Cost Management: Track spending, set budgets, and implement rate limiting for optimal resource utilization
- Smart Caching: Cache frequent responses to reduce API calls while maintaining Groq's speed advantage
- Spend Tracking: Track spend for individual API keys, users, and teams
Quick Start (2 minutes to hello world)
1. Install the package:
pip install litellm
2. Set up your API key:
export GROQ_API_KEY="your-groq-api-key"
3. Send your first request:
import os
import litellm
api_key = os.environ.get('GROQ_API_KEY')
response = litellm.completion(
model="groq/llama-3.3-70b-versatile",
messages=[
{"role": "user", "content": "hello from litellm"}
],
)
print(response)
Next Steps
For detailed setup of advanced features:
- Configuration of Spend Tracking for Keys, Users, and Teams
- Configuration for Budgets and Rate Limits
For more information on building production-ready applications with LiteLLM and Groq, see: