Your first API call

OPENAI_API_KEY=sk-...
MODEL_NAME=gpt-4.1-mini

python -m pip install openai python-dotenv

import os

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()
client = OpenAI()   # reads OPENAI_API_KEY from the environment automatically

response = client.chat.completions.create(
    model=os.getenv("MODEL_NAME", "gpt-4.1-mini"),
    messages=[
        {"role": "system", "content": "You are a concise AI tutor."},
        {"role": "user", "content": "Explain what an embedding is in one sentence."},
    ],
    temperature=0.2,
    max_tokens=100,
)

print(response.choices[0].message.content)
print("finish:", response.choices[0].finish_reason)
print("tokens:", response.usage.prompt_tokens, "in /", response.usage.completion_tokens, "out")

python first_call.py

ChatCompletion(
    id="chatcmpl-...",
    model="gpt-4.1-mini-2025-04-14",          # exact version that served you
    choices=[
        Choice(
            index=0,
            message=ChatCompletionMessage(role="assistant", content="An embedding is ..."),
            finish_reason="stop",
        )
    ],
    usage=CompletionUsage(prompt_tokens=31, completion_tokens=27, total_tokens=58),
)

import os

from dotenv import load_dotenv
from openai import OpenAI

load_dotenv()
client = OpenAI(timeout=60, max_retries=3)
DEFAULT_MODEL = os.getenv("MODEL_NAME", "gpt-4.1-mini")


def ask(prompt: str, system: str = "You are a helpful assistant.",
        model: str = DEFAULT_MODEL, temperature: float = 0.2,
        max_tokens: int = 500) -> str:
    response = client.chat.completions.create(
        model=model,
        messages=[
            {"role": "system", "content": system},
            {"role": "user", "content": prompt},
        ],
        temperature=temperature,
        max_tokens=max_tokens,
    )
    choice = response.choices[0]
    if choice.finish_reason == "length":
        print("warning: answer was truncated by max_tokens")
    return choice.message.content or ""


if __name__ == "__main__":
    print(ask("Give two bullet points on why tokens matter for cost."))

import openai
from openai import OpenAI

client = OpenAI(max_retries=2, timeout=30)

try:
    response = client.chat.completions.create(
        model="gpt-4.1-mini",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(response.choices[0].message.content)
except openai.AuthenticationError:
    print("Invalid or missing API key - check OPENAI_API_KEY.")
except openai.RateLimitError:
    print("Rate limit or quota exceeded - slow down or check billing.")
except openai.BadRequestError as err:
    print("Request rejected (bad model name, too many tokens, ...):", err.message)
except openai.APIConnectionError:
    print("Network problem - could not reach the API.")
except openai.APIStatusError as err:
    print("API error", err.status_code)

from openai import OpenAI

client = OpenAI()

stream = client.chat.completions.create(
    model="gpt-4.1-mini",
    messages=[{"role": "user", "content": "List three uses of LLMs, one line each."}],
    stream=True,
)

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

import os
from openai import OpenAI

PROVIDERS = {
    "openai":     {"base_url": None, "key": "OPENAI_API_KEY", "model": "gpt-4.1-mini"},
    "groq":       {"base_url": "https://api.groq.com/openai/v1", "key": "GROQ_API_KEY", "model": "llama-3.3-70b-versatile"},
    "openrouter": {"base_url": "https://openrouter.ai/api/v1", "key": "OPENROUTER_API_KEY", "model": "meta-llama/llama-3.3-70b-instruct"},
    "gemini":     {"base_url": "https://generativelanguage.googleapis.com/v1beta/openai/", "key": "GEMINI_API_KEY", "model": "gemini-2.5-flash"},
    "ollama":     {"base_url": "http://localhost:11434/v1", "key": None, "model": "llama3.2"},
}


def make_client(name: str) -> tuple[OpenAI, str]:
    cfg = PROVIDERS[name]
    api_key = os.getenv(cfg["key"]) if cfg["key"] else "ollama"   # local needs any string
    return OpenAI(base_url=cfg["base_url"], api_key=api_key), cfg["model"]


client, model = make_client("groq")
reply = client.chat.completions.create(
    model=model, messages=[{"role": "user", "content": "Say hi in five words."}]
)
print(reply.choices[0].message.content)

import anthropic

client = anthropic.Anthropic()          # reads ANTHROPIC_API_KEY

message = client.messages.create(
    model="claude-sonnet-4-5",
    max_tokens=300,
    system="You are a concise AI tutor.",
    messages=[{"role": "user", "content": "What is a context window?"}],
)

print(message.content[0].text)
print(message.stop_reason, message.usage.input_tokens, message.usage.output_tokens)

# install from https://ollama.com, then:
ollama pull llama3.2        # ~2 GB download
ollama run llama3.2 "Hello"  # quick test in the terminal