Claude Models

The following Claude models are available in the Anthropic workspace. Each model offers specific capabilities and features tailored to match your use case requirements. The “Reasoning” (Extended Thinking) capability is available only in the latest Claude 3.7 Sonnet model.

ModelsGenerate TextReasoningInput PDFInput ImageContext WindowMax OutputPlan@Giselle
claude-3-7-sonnet-20250219200k tokens8192 tokens (Extended: 64k/128k β)Pro
claude-3-5-sonnet-20241022200k tokens8192 tokensPro
claude-3-5-haiku-20241022200k tokens8192 tokensFree

Please note that some features may not be available within Giselle even if they are offered in the official API.

claude-3-7-sonnet-20250219

The most advanced model offering superior intelligence and reasoning capabilities. Ideal for handling complex tasks, extended reasoning, detailed analyses, and multimodal tasks involving PDFs and images. It includes an extensive context window of up to 200k tokens with optional extended thinking capabilities allowing outputs up to 64k tokens (128k tokens available in beta).

claude-3-5-sonnet-20241022

High-level intelligence model providing excellent general-purpose performance without extended reasoning capabilities. It supports multimodal inputs (PDF, images) and delivers robust text generation suitable for a wide range of applications with a context window of 200k tokens.

claude-3-5-haiku-20241022

Optimized for speed, this model is ideal for real-time responsiveness. It supports PDF and image inputs with rapid text generation, suitable for fast interactions and scenarios requiring quick, concise responses within a 200k token context window.

Model Selection Guide

Guidelines for selecting the optimal Claude model:

  • For best overall intelligence and complex reasoning: claude-3-7-sonnet-20250219
  • For general-purpose high-quality performance: claude-3-5-sonnet-20241022
  • When speed and immediate responsiveness matter: claude-3-5-haiku-20241022

Practices for Giselle

We recommend claude-3-7-sonnet-20250219 as your primary model in Giselle. It excels not only at code generation, architectural design, and technical reviews, but also produces remarkably natural text that reads authentically to human audiences. This versatile model can be effectively utilized across a broad spectrum of tasks, from creating engaging blog articles to writing complex code implementations.

For detailed specifications, performance benchmarks, or additional assistance, please refer to the Anthropic API Documentation.