claude_box #

An Anthropic (Claude) provider based on ai_box.

Usage #

import 'package:ai_box/ai_box.dart';
import 'package:claude_box/claude_box.dart';

Future<void> main() async {
  final ai = Claude(apiKey: 'sk-ant-...');

  // One-shot text generation.
  final answer = await ai.generateText(
    model: 'claude-sonnet-4-6',
    message: 'Say hello in one short sentence.',
  );
  print(answer);

  // Multi-turn chat.
  final res = await ai.chat(
    model: 'claude-sonnet-4-6',
    messages: [
      LLMContent.system('You are concise.'),
      LLMContent.user('What is the capital of Japan?'),
    ],
    maxTokens: 32,
  );
  print(res.text);
  print(res.usage); // token usage
}

Streaming #

True SSE streaming — text arrives incrementally and the final chunk carries the finish reason and token usage:

await for (final text in ai.generateTextStream(
  model: 'claude-sonnet-4-6',
  message: 'Write a haiku about Dart.',
)) {
  stdout.write(text);
}

Models and key validation #

final models = await ai.getModels();
final ok = await ai.validateKey();

Multimodal input (images, files), tool calling, structured output and the sealed LLMException error hierarchy are all provided by ai_box — see its README for details.