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 Haiku 4.5

Claude Haiku 4.5 matches Claude Sonnet 4's reasoning and coding strength while staying ultra-responsive for real-time and high-volume workloads. Extended thinking, controllable reasoning depth, and full tool-use support keep sub-agents fast without sacrificing quality.

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.

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 Fable 5

Claude Fable 5 is Anthropic's first publicly available Mythos-class model, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, offers reasoning support, and has a 1M-token context window. Designed for long-running, complex, and asynchronous tasks that previously required frequent human check-ins, it is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks, taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards that fall back to Claude Opus 4.8 on a small fraction of high-risk queries.

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 Haiku 4.5

Claude Haiku 4.5 matches Claude Sonnet 4's reasoning and coding strength while staying ultra-responsive for real-time and high-volume workloads. Extended thinking, controllable reasoning depth, and full tool-use support keep sub-agents fast without sacrificing quality.

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.

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 Fable 5

Claude Fable 5 is Anthropic's first publicly available Mythos-class model, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, offers reasoning support, and has a 1M-token context window. Designed for long-running, complex, and asynchronous tasks that previously required frequent human check-ins, it is particularly strong at end-to-end work that would otherwise take a person hours, days, or weeks, taking on problems that are long-running, ambiguous, or highly multi-step. It executes well-scoped tasks with few mistakes, automatically self-correcting through verification loops, and ships with robust safeguards that fall back to Claude Opus 4.8 on a small fraction of high-risk queries.