OpenAI Responses API vs Assistants API: which should you use?

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

# Responses API: YOU manage conversation history as an array
conversation = [
    {"role": "user", "content": "What's the capital of France?"},
    {"role": "assistant", "content": "The capital of France is Paris."},
    {"role": "user", "content": "What's its population?"}
]

# STATELESS: full context sent each call
response = client.chat.completions.create(
    model="gpt-4o",
    messages=conversation  # You control this array: add/remove as needed
)

print(response.choices[0].message.content)

# To continue, you append the response and send again
conversation.append({"role": "assistant", "content": response.choices[0].message.content})
conversation.append({"role": "user", "content": "Tell me more."})

response2 = client.chat.completions.create(model="gpt-4o", messages=conversation)
print(response2.choices[0].message.content)

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ.get("OPENAI_API_KEY"))

# Assistants API: create a Thread (conversation container)
thread = client.beta.threads.create()
thread_id = thread.id

# Add first user message
client.beta.threads.messages.create(
    thread_id=thread_id,
    role="user",
    content="What's the capital of France?"
)

# Run assistant (server retrieves history automatically)
assistant_id = "asst_xxxxx"  # Your pre-configured assistant
run = client.beta.threads.runs.create(thread_id=thread_id, assistant_id=assistant_id)

# Poll for completion
import time
while run.status != "completed":
    run = client.beta.threads.runs.retrieve(thread_id=thread_id, run_id=run.id)
    time.sleep(0.5)

# Get latest message (server-managed history)
messages = client.beta.threads.messages.list(thread_id=thread_id)
print(messages.data[0].content[0].text)

# Add second user message: history is automatic
client.beta.threads.messages.create(
    thread_id=thread_id,
    role="user",
    content="What's its population?"
)

run2 = client.beta.threads.runs.create(thread_id=thread_id, assistant_id=assistant_id)
while run2.status != "completed":
    run2 = client.beta.threads.runs.retrieve(thread_id=thread_id, run_id=run2.id)
    time.sleep(0.5)

messages2 = client.beta.threads.messages.list(thread_id=thread_id)
print(messages2.data[0].content[0].text)