Claude 3.5 Haiku
by Anthropic
Fastest model that surpasses Claude 3 Opus intelligence on many benchmarks while maintaining speed and cost efficiency. Achieves 40.6% on SWE-bench Verified despite being optimized for rapid responses and high-volume applications.
- Superior intelligence outperforming Claude 3 Opus on numerous benchmarks while maintaining speed
- Exceptional coding capabilities for a compact model with 40.6% SWE-bench Verified performance
- Near-instant responses optimized for real-time applications and user-facing products
- Enhanced tool use and instruction following compared to predecessors
- Cost-effective solution ideal for high-volume data processing and automated workflows
JSON Mode
Output responses in valid JSON format.
Web Search
Search the web for current info.
Model Information
Supported Formats
Claude Opus 4.8Anthropic's most capable model released May 2026. Hybrid reasoning model with a 1M token context window, stronger across coding, agentic tasks, and professional work over Opus 4.7. Features adaptive thinking via the effort parameter (defaults to high). Knowledge cutoff January 2026.
Claude Opus 4.7Anthropic's most capable generally available model with a step-change improvement in agentic coding over Claude Opus 4.6. Features 1M token context window, 128K max output, and adaptive thinking. Knowledge cutoff January 2026.
Claude Opus 4.6Anthropic's most intelligent model released February 2026. Features 1M token context window and 128K max output. Built for deep reasoning, long-horizon agentic tasks, and complex multi-step coding workflows. Supports extended thinking and adaptive thinking modes.