Free LLM APIs for Python: SDK Setup, Streaming & Function Calling

Start by installing the official client libraries in your virtual environment:

pip install openai google-genai groq python-dotenv tenacity

Using python-dotenv allows seamless credential loading from your local .env file.

Groq delivers instant token generation, making it the premier choice for terminal CLIs and chat interfaces:

```python import os from groq import Groq from dotenv import load_dotenv

load_dotenv() client = Groq(api_key=os.environ.get("GROQ_API_KEY"))

stream = client.chat.completions.create( model="llama-3.3-70b-versatile", messages=[{"role": "user", "content": "Write a Python decorator for caching API responses."}], temperature=0.2, max_tokens=1024, stream=True )

for chunk in stream: content = chunk.choices[0].delta.content if content: print(content, end="", flush=True) print() ```

Google's unified 2026 SDK (google-genai) handles Gemini 2.0 Flash with native typing:

```python import os from google import genai from dotenv import load_dotenv

load_dotenv() client = genai.Client(api_key=os.environ.get("GEMINI_API_KEY"))

response = client.models.generate_content( model="gemini-2.0-flash", contents="Summarize the differences between dense and sparse Mixture of Experts (MoE)." )

print(response.text) ```

Ensuring guaranteed schema compliance without paying for closed frontier models:

```python import os from pydantic import BaseModel from openai import OpenAI

class TechStackRecommendation(BaseModel): frontend: str backend: str database: str rationale: str

client = OpenAI( base_url="https://api.groq.com/openai/v1", api_key=os.environ.get("GROQ_API_KEY") )

completion = client.beta.chat.completions.parse( model="llama-3.3-70b-versatile", messages=[{"role": "user", "content": "Recommend a stack for a high-volume real-time analytics dashboard."}], response_format=TechStackRecommendation, )

parsed = completion.choices[0].message.parsed print(f"Backend: {parsed.backend} | DB: {parsed.database}") ```