Anthropic: Claude Sonnet 4.5 API
Claude Sonnet 4.5 is a cutting-edge model from Anthropic, specifically optimized for real-world complex agents and high-intensity coding workflows. Marketed as the "best coding model in the world," it sets new state-of-the-art records on benchmarks like SWE-bench Verified. It delivers generational leaps in computer use, web search, financial analysis, and cybersecurity tasks. A key innovation is its ability to maintain autonomous focus for over 30 hours on long-running tasks. It introduces an "Extended Thinking" mode for deep reasoning and maintains the competitive pricing of its predecessors, offering an unmatched balance of intelligence and cost-efficiency.
- Context window: 1,000,000 tokens
- Max output: 64,000 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-09-29
- Knowledge cutoff: 2025-06-30
Frequently Asked Questions
What is the context window of Claude Sonnet 4.5?
Claude Sonnet 4.5 supports a context window of up to 1,000,000 tokens.
Does Claude Sonnet 4.5 support function calling?
Yes. Claude Sonnet 4.5 supports tool / function calling.
Does Claude Sonnet 4.5 support reasoning?
Yes. Claude Sonnet 4.5 is a reasoning-capable model.
What is the knowledge cutoff of Claude Sonnet 4.5?
The knowledge cutoff of Claude Sonnet 4.5 is 2025-06-30.