Chat completions

client.chat.complete() sends a single request and resolves with the full response.

Basic usage

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

console.log(response.choices[0].message.content);

Parameters

Parameter	Type	Required	Description
model	string	Yes	auto for automatic selection, or a specific model identifier, e.g. gpt-4o, claude-sonnet-4-6
messages	ChatMessage[]	Yes	Conversation history
temperature	number	No	Sampling temperature 0–2
maxTokens	number	No	Maximum tokens in the response
provider	string	No	Force a specific provider, e.g. openai, anthropic

Targeting a specific provider

By default AICP selects the provider according to your routing configuration. You can pin a request to a provider:

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

Multi-turn conversations

const messages: ChatMessage[] = [
  { role: 'system', content: 'You are a helpful assistant.' },
];

async function chat(userMessage: string) {
  messages.push({ role: 'user', content: userMessage });

  const response = await client.chat.complete({ model: 'auto', messages });
  const reply = response.choices[0].message;

  messages.push(reply);
  return reply.content;
}

console.log(await chat('What is 2 + 2?'));
console.log(await chat('And multiply that by 10?'));

Response shape

{
  id:      'chatcmpl-…',
  object:  'chat.completion',
  model:   'gpt-4o-mini',
  choices: [
    {
      index:         0,
      message:       { role: 'assistant', content: '…' },
      finish_reason: 'stop',
    },
  ],
  usage: {
    prompt_tokens:     10,
    completion_tokens: 42,
    total_tokens:      52,
  },
}