Chat completions

client.chat.complete() sends a request and returns the full response as a dict.

Basic usage

response = client.chat.complete(
    model="auto",
    messages=[
        {"role": "system",  "content": "You are a helpful assistant."},
        {"role": "user",    "content": "Explain quantum computing in one sentence."},
    ],
)

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

Parameters

Parameter	Type	Required	Description
model	str	Yes	auto for automatic selection, or a specific model identifier, e.g. gpt-4o, claude-sonnet-4-6
messages	list[ChatMessage]	Yes	Conversation history
temperature	float | None	No	Sampling temperature 0–2
max_tokens	int | None	No	Maximum tokens in the response
provider	str | None	No	Force a specific provider, e.g. anthropic

Targeting a specific provider

response = client.chat.complete(
    model="claude-haiku-4-5-20251001",
    messages=[{"role": "user", "content": "Hello!"}],
    provider="anthropic",
)

Multi-turn conversations

messages = [{"role": "system", "content": "You are a helpful assistant."}]

def chat(user_message: str) -> str:
    messages.append({"role": "user", "content": user_message})
    response = client.chat.complete(model="auto", messages=messages)
    reply = response["choices"][0]["message"]
    messages.append(reply)
    return reply["content"]

print(chat("What is 2 + 2?"))
print(chat("And multiply that by 10?"))