Claude Sonnet 4.5

Claude Sonnet 4.5 is Anthropic’s active legacy Sonnet model for coding, reasoning, visual analysis and tool-using workflows.

Claude Sonnet 4.5 verified specifications

Anthropic lists the exact Claude API ID claude-sonnet-4-5-20250929, a 200,000-token context window, up to 64,000 output tokens, text and image input, and extended thinking.

Pricing and availability

Standard pricing is $3 per million input tokens and $15 per million output tokens. The model remains available across the Claude API and major cloud platforms, although Anthropic recommends migrating new workloads to newer Sonnet models.

Best uses

It remains useful for coding, document analysis, visual reasoning, tool workflows and applications already tuned around Sonnet 4.5 behavior.

Limitations

It has legacy status, a smaller context window than current Claude models and a January 2025 reliable knowledge cutoff.

Claude Sonnet 4.5 capabilities and use cases

In addition, its main capabilities include 200K context, 64K output, Text and image input, Extended thinking, Tool use and Structured outputs. For example, common use cases include Software engineering, Document Q&A, Visual reasoning, Enterprise assistants and Migration compatibility.

Who should consider Claude Sonnet 4.5?

In practice, this model may suit Coding, Document analysis, Vision tasks, Tool-using assistants and Legacy Claude integrations. Also, notable strengths include Strong coding and reasoning, Vision input, Mature tool support and Still available on major cloud platforms. However, review trade-offs such as Anthropic recommends migration to newer Sonnet models, Static knowledge cutoff and Important outputs still require review before adopting it.

Claude Sonnet 4.5 pricing and access

Meanwhile, Claude Sonnet 4.5 remains available as a legacy model at $3 per 1M input tokens and $15 per 1M output tokens; prompt caching and Batch API have separate rates. Standard API pricing is $3/M input and $15/M output. It is still active, but Anthropic recommends newer Sonnet models for new deployments.

Official resources and verification

Use the official model website, official documentation, pricing or release source and additional primary source to confirm current availability, limits and pricing. Product details can change after publication, so rely on primary documentation for final decisions.

Compare with other AI models

Next, continue your research in the AI models directory, Anthropic models and General Purpose Language Model models. Compare providers, pricing, modalities and practical limitations side by side to choose the right model for your workflow.