Chapter 02
Welcome to the Second Lab - Week 1, Day 3
Notebook.venv39 cells
Welcome to the Second Lab - Week 1, Day 3
Today we will work with lots of models! This is a way to get comfortable with APIs.
In [ ]python · cell 3
python
# Start with imports - ask the Cursor Agent to explain any package that you don't know
import os
import json
from dotenv import load_dotenv
from openai import OpenAI
from IPython.display import Markdown, displayIn [ ]python · cell 4
python
# Always remember to do this!
load_dotenv(override=True)In [ ]python · cell 5
python
# Print the key prefixes to help with any debugging
openai_api_key = os.getenv('OPENAI_API_KEY')
anthropic_api_key = os.getenv('ANTHROPIC_API_KEY')
google_api_key = os.getenv('GOOGLE_API_KEY')
deepseek_api_key = os.getenv('DEEPSEEK_API_KEY')
groq_api_key = os.getenv('GROQ_API_KEY')
grok_api_key = os.getenv('GROK_API_KEY')
openrouter_api_key = os.getenv('OPENROUTER_API_KEY')
if openai_api_key:
print(f"OpenAI API Key exists and begins {openai_api_key[:8]}")
else:
print("OpenAI API Key not set")
if anthropic_api_key:
print(f"Anthropic API Key exists and begins {anthropic_api_key[:7]}")
else:
print("Anthropic API Key not set (and this is optional)")
if google_api_key:
print(f"Google API Key exists and begins {google_api_key[:2]}")
else:
print("Google API Key not set (and this is optional)")
if deepseek_api_key:
print(f"DeepSeek API Key exists and begins {deepseek_api_key[:3]}")
else:
print("DeepSeek API Key not set (and this is optional)")
if groq_api_key:
print(f"Groq API Key exists and begins {groq_api_key[:4]}")
else:
print("Groq API Key not set (and this is optional)")
if grok_api_key:
print(f"Grok API Key exists and begins {grok_api_key[:4]}")
else:
print("Grok API Key not set (and this is optional)")
if openrouter_api_key:
print(f"OpenRouter API Key exists and begins {openrouter_api_key[:6]}")
else:
print("OpenRouter API Key not set (and this is optional)")In [ ]python · cell 6
python
request = """
Please come up with a challenging, nuanced question with a succinct answer,
that I can ask a number of LLMs to evaluate their intelligence.
Not a mathematical puzzle, but more of a thought-provoking question that requires intelligent insight.
Include in your question that the answer must be short.
"""
request += "Answer only with the question, no explanation."
messages = [{"role": "user", "content": request}]In [ ]python · cell 7
python
messagesIn [ ]python · cell 8
python
openai = OpenAI()
response = openai.chat.completions.create(model="gpt-5.4-mini", messages=messages)
question = response.choices[0].message.content
display(Markdown(question))Calling LLMs from multple providers
We are about to call LLMs from many other providers. They all provide API endpoints that are compatible with OpenAI, as explained in Guide 9 in the guides folder. So we can simply use these endpoints as if we are using OpenAI.
Please note:
I'm going to use lots of LLMs from different providers, but you don't need to! This is only to show their abilities.
In [ ]python · cell 10
python
# OpenAI Compatible URLs
ANTHROPIC_BASE_URL = "https://api.anthropic.com/v1/"
DEEPSEEK_BASE_URL = "https://api.deepseek.com/v1"
GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta/openai/"
GROQ_BASE_URL = "https://api.groq.com/openai/v1"
GROK_BASE_URL = "https://api.x.ai/v1"
OPENROUTER_BASE_URL = "https://openrouter.ai/api/v1"
OLLAMA_BASE_URL = "http://localhost:11434/v1"In [ ]python · cell 11
python
# OpenAI client libraries with the right base_url and key
# If this surprises you, please see Guide 9 in the Guides folder!
anthropic = OpenAI(api_key=anthropic_api_key, base_url=ANTHROPIC_BASE_URL)
deepseek = OpenAI(api_key=deepseek_api_key, base_url=DEEPSEEK_BASE_URL)
gemini = OpenAI(api_key=google_api_key, base_url=GEMINI_BASE_URL)
groq = OpenAI(api_key=groq_api_key, base_url=GROQ_BASE_URL)
grok = OpenAI(api_key=grok_api_key, base_url=GROK_BASE_URL)
openrouter = OpenAI(api_key=openrouter_api_key, base_url=OPENROUTER_BASE_URL)
ollama = OpenAI(base_url=OLLAMA_BASE_URL, api_key="ollama")In [ ]python · cell 12
python
competitors = []
answers = []
messages = [{"role": "user", "content": question}]In [ ]python · cell 13
python
def record(model_name, answer):
competitors.append(model_name)
answers.append(answer)
display(Markdown(answer))In [ ]python · cell 14
python
# The API we know well
# Reasoning effort can be none, low, medium, high, or xhigh
model_name = "gpt-5.4-nano"
response = openai.chat.completions.create(model=model_name, messages=messages, reasoning_effort="none")
answer = response.choices[0].message.content
record(model_name, answer)In [ ]python · cell 15
python
model_name = "claude-sonnet-4-6"
response = anthropic.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
record(model_name, answer)In [ ]python · cell 16
python
model_name = "gemini-3.1-flash-lite"
response = gemini.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
record(model_name, answer)In [ ]python · cell 17
python
model_name = "deepseek-v4-flash"
response = deepseek.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
record(model_name, answer)In [ ]python · cell 18
python
model_name = "openai/gpt-oss-120b"
response = groq.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
display(Markdown(answer))
competitors.append(model_name)
answers.append(answer)In [ ]python · cell 19
python
model_name = "moonshotai/kimi-k2.6"
response = openrouter.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
record(model_name, answer)For the next cell, we will use Ollama
Ollama runs a local web service that gives an OpenAI compatible endpoint,
and runs models locally using high performance C++ code.
If you don't have Ollama, install it here by visiting https://ollama.com then pressing Download and following the instructions.
After it's installed, you should be able to visit here: http://localhost:11434 and see the message "Ollama is running"
You might need to restart Cursor (and maybe reboot). Then open a Terminal (control+`) and run ollama serve
Useful Ollama commands (run these in the terminal, or with an exclamation mark in this notebook):
ollama pull <model_name> downloads a model locally
ollama ls lists all the models you've downloaded
ollama rm <model_name> deletes the specified model from your downloads
In [ ]python · cell 22
python
!ollama pull llama3.2In [ ]python · cell 23
python
import requests
requests.get('http://localhost:11434').contentIn [ ]python · cell 24
python
import requests
models = requests.get('http://localhost:11434/v1/models').json()
for model in models.get("data"):
print(model.get("id"))In [ ]python · cell 25
python
model_name = "llama3.2:1b"
response = ollama.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
record(model_name, answer)In [ ]python · cell 26
python
model_name = "gpt-oss:latest"
response = ollama.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
display(Markdown(answer))
competitors.append(model_name)
answers.append(answer)In [ ]python · cell 27
python
model_name = "gemma4:latest"
response = ollama.chat.completions.create(model=model_name, messages=messages)
answer = response.choices[0].message.content
display(Markdown(answer))
competitors.append(model_name)
answers.append(answer)In [ ]python · cell 28
python
# So where are we?
print(len(competitors))
print(competitors)
print(answers)In [ ]python · cell 29
python
# It's nice to know how to use "zip"
for competitor, answer in zip(competitors, answers):
print(f"Competitor: {competitor}\n\n{answer}")In [ ]python · cell 30
python
# Let's bring this together - note the use of "enumerate"
together = ""
for index, answer in enumerate(answers):
together += f"# Response from competitor {index+1}\n\n"
together += answer + "\n\n"In [ ]python · cell 31
python
print(together)In [ ]python · cell 32
python
judge = f"""You are judging a competition between {len(competitors)} competitors.
Each model has been given this question:
{question}
Your job is to evaluate each response for clarity and strength of argument, and rank them in order of best to worst.
Respond with JSON, and only JSON, with the following format:
{{"results": ["best competitor number", "second best competitor number", "third best competitor number", ...]}}
Here are the responses from each competitor:
{together}
Now respond with the JSON with the ranked order of the competitors, nothing else. Do not include markdown formatting or code blocks."""In [ ]python · cell 33
python
print(judge)In [ ]python · cell 34
python
judge_messages = [{"role": "user", "content": judge}]And now for Grok!
Branded as "The most truth-seeking large language model in the world".. so let's use it as our LLM as a judge
In [ ]python · cell 36
python
# Judgement time!
# Grok is "The most truth-seeking large language model in the world."
model_name = "grok-4.3"
response = grok.chat.completions.create(model=model_name, messages=judge_messages)
results = response.choices[0].message.content
print(results)In [ ]python · cell 37
python
# OK let's turn this into results!
results_dict = json.loads(results)
ranks = results_dict["results"]
for index, result in enumerate(ranks):
competitor = competitors[int(result)-1]
print(f"Rank {index+1}: {competitor}")