Chat Completion

ELI5 — The Vibe Check

Chat Completion is the API pattern for having a back-and-forth conversation with an AI. You send an array of messages (user says X, assistant says Y, user says Z) and the AI generates the next message. It's the fundamental API call behind every chatbot, coding assistant, and AI feature you've ever built.

Real Talk

The Chat Completions API (used by OpenAI, Anthropic, and others) accepts a list of messages with roles (system, user, assistant) and returns the model's next message. It is the dominant interface for LLM integration, supporting multi-turn conversation, system prompts, tool use, and streaming. Most AI products are built on top of this pattern.

Show Me The Code

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is 2+2?"},
        {"role": "assistant", "content": "4"},
        {"role": "user", "content": "Now multiply that by 10."}
    ]
)
print(response.choices[0].message.content)

When You'll Hear This

"The frontend calls the chat completion endpoint." / "Chat completion supports multi-turn conversations."