Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, offers reasoning support, and has a 1M-token context window. Built for highly autonomous agents, long-horizon agentic work, and memory-driven tasks where coherence over extended sessions matters, it is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration across large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data while maintaining quality across very long outputs.

Claude Opus 4.5

Claude Opus 4.5 model integrated via automation on 2025-11-24

Claude Sonnet 4.5

Claude Sonnet 4.5 is Anthropic's most advanced Sonnet model to date, optimized for real-world agents and coding workflows. Stronger agentic capabilities, speculative parallel execution, efficient memory and tool orchestration.

Golden Gate Claude

A temporary research demo version of Claude 3 Sonnet (active for 24 hours on May 23, 2024) specifically engineered by Anthropic to demonstrate feature steering. The model was manipulated to obsessively focus on the Golden Gate Bridge in its responses, showcasing research into model interpretability and safety.

Claude Opus 5

Claude Opus 5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents. It holds instruction following and tool use steady across extended tasks while staying effective at lower effort settings when latency and token efficiency matter.

Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.

Claude Opus 4.8

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, offers reasoning support, and has a 1M-token context window. Built for highly autonomous agents, long-horizon agentic work, and memory-driven tasks where coherence over extended sessions matters, it is particularly strong on multi-step reasoning, complex coding, and end-to-end project orchestration across large codebases, multi-stage debugging, and long-running asynchronous agent pipelines. Beyond coding, it handles knowledge work such as drafting documents, building presentations, and analyzing data while maintaining quality across very long outputs.

Claude Opus 4.5

Claude Opus 4.5 model integrated via automation on 2025-11-24

Claude Sonnet 4.5

Claude Sonnet 4.5 is Anthropic's most advanced Sonnet model to date, optimized for real-world agents and coding workflows. Stronger agentic capabilities, speculative parallel execution, efficient memory and tool orchestration.

Golden Gate Claude

A temporary research demo version of Claude 3 Sonnet (active for 24 hours on May 23, 2024) specifically engineered by Anthropic to demonstrate feature steering. The model was manipulated to obsessively focus on the Golden Gate Bridge in its responses, showcasing research into model interpretability and safety.

Claude Opus 5

Claude Opus 5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis of charts and documents, complex office deliverables, and coordinating parallel subagents. It holds instruction following and tool use steady across extended tasks while staying effective at lower effort settings when latency and token efficiency matter.

Claude Sonnet 5

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max, and x-high), a 1M-token context window, and text, image, and file inputs. Sonnet 5 uses an updated tokenizer and includes real-time cyber safeguards that block certain high-risk dual-use activities.