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 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 4.7

Anthropic's next-generation Opus model, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. Especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration. Beyond coding, brings improved knowledge work capabilities from drafting documents and building presentations to analyzing data. Maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.

Claude Sonnet 4.6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Claude Opus 4.6

Anthropic's strongest model for coding and long-running professional tasks. Built for agents that operate across entire workflows rather than single prompts, excelling at large codebases, complex refactors, and multi-step debugging. Shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks. Also excels at sustained knowledge work, producing near-production-ready documents, plans, and analyses in a single pass.

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 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 4.7

Anthropic's next-generation Opus model, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on complex, multi-step tasks and more reliable agentic execution across extended workflows. Especially effective for asynchronous agent pipelines where tasks unfold over time - large codebases, multi-stage debugging, and end-to-end project orchestration. Beyond coding, brings improved knowledge work capabilities from drafting documents and building presentations to analyzing data. Maintains coherence across very long outputs and extended sessions, making it a strong default for tasks that require persistence, judgment, and follow-through.

Claude Sonnet 4.6

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with memory, polished document creation, and confident computer use for web QA and workflow automation.

Claude Opus 4.6

Anthropic's strongest model for coding and long-running professional tasks. Built for agents that operate across entire workflows rather than single prompts, excelling at large codebases, complex refactors, and multi-step debugging. Shows deeper contextual understanding, stronger problem decomposition, and greater reliability on hard engineering tasks. Also excels at sustained knowledge work, producing near-production-ready documents, plans, and analyses in a single pass.