Chat completions

resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[
        {"role": "system", "content": "You are a senior staff engineer."},
        {"role": "user", "content": "Pros and cons of postgres LISTEN/NOTIFY for a job queue?"},
    ],
    temperature=0.4,
    max_tokens=800,
)
print(resp.choices[0].message.content)

stream = client.chat.completions.create(
    model="gemini-2-5-pro",
    messages=[{"role": "user", "content": "Explain B-trees in one paragraph."}],
    stream=True,
)

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

tools = [{
    "type": "function",
    "function": {
        "name": "get_current_weather",
        "description": "Get current weather for a city",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string"},
                "unit": {"type": "string", "enum": ["c", "f"]},
            },
            "required": ["city"],
        },
    },
}]

resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools,
    tool_choice="auto",
)

# Inspect tool calls the model wants to make
for call in resp.choices[0].message.tool_calls or []:
    print(call.function.name, call.function.arguments)

# Pass an image URL or a base64 data URI as part of a multimodal message
resp = client.chat.completions.create(
    model="gemini-2-5-pro",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {"type": "image_url", "image_url": {
                "url": "https://example.com/cat.jpg"
            }},
        ],
    }],
)
print(resp.choices[0].message.content)

# Claude's "extended thinking" mode + Gemini "thinking" mode both surface
# reasoning_tokens in usage. You're billed for them at the output rate.
resp = client.chat.completions.create(
    model="claude-opus-4-7",
    messages=[{"role": "user", "content": "Plan a 3-week MLOps migration."}],
)
print(resp.usage.completion_tokens_details.reasoning_tokens)

# Claude caches prefixes you mark with cache_control. Attach it to a content
# block; later calls reusing that prefix read it at ~10% of the input price.
resp = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": LONG_DOCUMENT,            # the stable, reused prefix
                "cache_control": {"type": "ephemeral"},
            },
            {"type": "text", "text": "Summarize the document above."},
        ],
    }],
)
print(resp.usage.prompt_tokens_details.cached_tokens)

from openai import OpenAI

# Before — Ollama's OpenAI-compatible API, local models
client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="ollama",                       # ignored locally
)
resp = client.chat.completions.create(
    model="llama3.2",
    messages=[{"role": "user", "content": "Summarize this changelog."}],
)

# After — the same call against hosted frontier models.
# Two lines changed. Everything below them is untouched.
client = OpenAI(
    base_url="https://api.kunavo.com/v1",   # <- was localhost:11434/v1
    api_key=os.environ["KUNAVO_API_KEY"],
)
resp = client.chat.completions.create(
    model="claude-sonnet-4-6",              # <- was llama3.2
    messages=[{"role": "user", "content": "Summarize this changelog."}],
)