Models overview
模型總覽
Claude is a family of state-of-the-art large language models developed by Anthropic. This guide introduces our models and compares their performance.
Claude 是由 Anthropic 開發的一系列最先進大型語言模型。本指南介紹我們的模型並比較其性能。
Choosing a model
選擇模型
If you're unsure which model to use, we recommend starting with Claude Sonnet 4.5. It offers the best balance of intelligence, speed, and cost for most use cases, with exceptional performance in coding and agentic tasks.
如果你不確定要使用哪個模型，我們建議從 Claude Sonnet 4.5 開始。對於大多數使用場景，它提供智慧、速度和成本的最佳平衡，在程式設計和 agent 任務方面表現出色。
All current Claude models support text and image input, text output, multilingual capabilities, and vision. Models are available via the Anthropic API, AWS Bedrock, and Google Vertex AI.
所有目前的 Claude 模型都支援文字和圖片輸入、文字輸出、多語言能力和視覺功能。模型可透過 Anthropic API、AWS Bedrock 和 Google Vertex AI 取得。
Latest models comparison
最新模型比較
| Feature | Claude Sonnet 4.5 | Claude Haiku 4.5 | Claude Opus 4.5 |
|---|---|---|---|
| Description | Our smart model for complex agents and coding | Our fastest model with near-frontier intelligence | Premium model combining maximum intelligence with practical performance |
| Claude API ID | claude-sonnet-4-5-20250929 | claude-haiku-4-5-20251001 | claude-opus-4-5-20251101 |
| Pricing | $3 / input MTok, $15 / output MTok | $1 / input MTok, $5 / output MTok | $5 / input MTok, $25 / output MTok |
| Extended thinking | Yes | Yes | Yes |
| Comparative latency | Fast | Fastest | Moderate |
| Context window | 200K tokens / 1M tokens (beta) | 200K tokens | 200K tokens |
| Max output | 64K tokens | 64K tokens | 64K tokens |
| 特性 | Claude Sonnet 4.5 | Claude Haiku 4.5 | Claude Opus 4.5 |
|---|---|---|---|
| 描述 | 適用於複雜 agent 和程式設計的智慧模型 | 具有接近前沿智慧的最快模型 | 結合最高智慧與實用性能的頂級模型 |
| Claude API ID | claude-sonnet-4-5-20250929 | claude-haiku-4-5-20251001 | claude-opus-4-5-20251101 |
| 定價 | $3 / 輸入 MTok、$15 / 輸出 MTok | $1 / 輸入 MTok、$5 / 輸出 MTok | $5 / 輸入 MTok、$25 / 輸出 MTok |
| Extended thinking | 是 | 是 | 是 |
| 相對延遲 | 快 | 最快 | 中等 |
| Context window | 200K tokens / 1M tokens（beta） | 200K tokens | 200K tokens |
| 最大輸出 | 64K tokens | 64K tokens | 64K tokens |
Legacy models
舊版模型
The following models are still available but we recommend migrating to current models for improved performance:
以下模型仍然可用，但我們建議遷移至目前的模型以獲得更好的性能：
- Claude Opus 4.1
- Claude Sonnet 4
- Claude Sonnet 3.7
- Claude Opus 4
- Claude Haiku 3
- Claude Opus 4.1
- Claude Sonnet 4
- Claude Sonnet 3.7
- Claude Opus 4
- Claude Haiku 3
Prompt and output performance
提示詞與輸出性能
Claude 4 models excel in:
Claude 4 模型在以下方面表現出色：
- Performance: Top-tier results in reasoning, coding, multilingual tasks, long-context handling, honesty, and image processing.
- Engaging responses: Claude models are ideal for applications that require rich, human-like interactions.
- Output quality: When migrating from previous model generations to Claude 4, you may notice larger improvements in overall performance.
- 性能：在推理、程式設計、多語言任務、長文本處理、誠實度和圖像處理方面達到頂級水準。
- 引人入勝的回應：Claude 模型非常適合需要豐富、類人互動的應用。
- 輸出品質：從先前的模型世代遷移到 Claude 4 時，你可能會注意到整體性能的大幅提升。
Migrating to Claude 4.5
遷移至 Claude 4.5
If you're currently using Claude 3 models, we recommend migrating to Claude 4.5 to take advantage of improved intelligence and enhanced capabilities.
如果你目前使用的是 Claude 3 模型，我們建議遷移至 Claude 4.5 以利用改進的智慧和增強的能力。
Get started with Claude
開始使用 Claude
If you're ready to start exploring what Claude can do for you, let's dive in! Whether you're a developer looking to integrate Claude into your applications or a user wanting to experience the power of AI firsthand, we've got you covered.
如果你準備好開始探索 Claude 能為你做什麼，讓我們開始吧！無論你是想將 Claude 整合到應用程式中的開發者，還是想親身體驗 AI 強大功能的使用者，我們都能滿足你的需求。