Claude API Integration
Available Models
Claude Sonnet 4
The latest flagship model excelling in coding with 72.7% on SWE-bench. Supports up to 64K output tokens and powers GitHub Copilot.
- • API Name: claude-sonnet-4-20250514
- • $3 per million input tokens, $15 per million output tokens
- • Up to 90% cost savings with prompt caching
- • Training cutoff: March 2025
Claude Opus 4
The world's best coding model, leading on SWE-bench (72.5%) and Terminal-bench (43.2%). Maximum output of 32,000 tokens.
- • API Name: claude-opus-4
- • $15 per million input tokens, $75 per million output tokens
- • Max output: 32,000 tokens
- • Training cutoff: March 2025
Claude 3.7 Sonnet
The first hybrid reasoning model. Can switch between normal responses and extended thinking mode for complex tasks.
- • API Name: claude-3-7-sonnet
- • $3 per million input tokens, $15 per million output tokens
- • Extended thinking mode available
- • Up to 128K thinking tokens
Claude 3.5 Sonnet
Outperforms Claude 3 Opus on evaluations while operating at twice the speed. 200K token context window with strong performance.
- • API Name: claude-3-5-sonnet-v2@20241022
- • $3 per million input tokens, $15 per million output tokens
- • 200K context window
- • Solved 64% of agentic coding problems
Claude 3.5 Haiku
The fastest model in the family with 200K token context window, ideal for rapid processing tasks.
- • API Name: claude-3-5-haiku@20241022
- • $1 per million input tokens, $5 per million output tokens
- • 200K context window
- • Trained until July 2024
Claude 3 Opus
The most powerful Claude 3 model for complex tasks, ideal for research and development applications.
- • API Name: claude-3-opus@20240229
- • $15 per million input tokens, $75 per million output tokens
- • 200K context window
- • Premium tier performance
⚠️ Important Notice
Information about models, pricing, and features may be outdated or incorrect. Always consult the official provider documentation for the most current and accurate data.
Key Features
Claude models represent the cutting edge of AI capabilities with world-class coding performance, reasoning abilities, and hybrid thinking modes.
- • World's best coding model (Claude Opus 4)
- • Hybrid reasoning with extended thinking mode
- • Up to 90% cost savings with prompt caching
- • 50% cost savings with batch processing
- • Available on Claude.ai, iOS app, and API
- • Compatible with Amazon Bedrock and Google Cloud Vertex AI
- • Advanced reasoning and multi-step problem solving
- • Multimodal capabilities (text and images)