Anthropic has released Opus 4.5, improving conversation continuity in its Claude models by summarizing earlier dialogue instead of abruptly ending chats. The new model also achieves an 80.9% accuracy score, surpassing OpenAI's GPT-5.1 in coding tasks, though it still trails in visual reasoning.

Anthropic has blocked opencode access from its Claude Code API, prompting frustration among users. This move raises concerns about the company's reliability and suggests they may restrict access for non-compliant users. The author warns that this could push users toward alternative model providers.

Vercel now allows users to access Claude Code through its AI Gateway using an Anthropic-compatible API. This setup centralizes usage, tracks spending, and provides failover options between different models. Users need to set specific environment variables to configure the integration.

The article announces the launch of Claude Code, a new tool by Anthropic that allows developers to integrate AI capabilities into their applications through a simple code interface. It emphasizes user-friendly API access that facilitates the development of smarter applications leveraging Claude's advanced capabilities. The tool aims to enhance productivity and innovation in software development.