To avoid high API costs, use the OAuth method to link OpenClaw to your existing $20 ChatGPT subscription. This leverages your subscription's usage limits instead of per-token API pricing. Crucially, configure fallback models (like Anthropic or an open-source model via OpenRouter) so your agent remains operational if the primary model fails.

Counterintuitively, a model optimized for writing (GPT 5.1 High) excels at the planning stage in Cursor's "plan mode" due to its strength in logical thinking and step-by-step reasoning. For the actual code execution, switch to a coding-specific model like Sonnet.

Instead of traditional note-taking apps, using an AI-native code editor like Cursor to manage an AI's configuration and knowledge files provides powerful inline AI editing and referencing capabilities for prose, not just code.

Cursor discovered that agents need more than just code access. Providing a full VM environment—a "brain in a box" where they can see pixels, run code, and use dev tools like a human—was the step-change needed to tackle entire features, not just minor edits.

When working with multiple repositories, opening the entire project directory in your IDE allows AI tools to traverse all repos. This provides more contextualized answers to complex questions that span multiple services, avoiding siloed analysis and improving AI assistant performance.

The term "OpenAI-compatible" is ambiguous for local backends. It can mean anything from accepting a similar request shape to partially working streaming. True compatibility with modern clients requires state, lifecycle management, and strict event semantics, a much higher bar that most simple endpoints fail to meet.

With 80% of revenue tied to token usage, leading model providers are not incentivized to offer features like auto-routing to cheaper models. This business model conflict creates a competitive vulnerability and an opportunity for third-party tools like Cursor to win by optimizing developer experience and cost-efficiency.

In a significant strategic move, OpenAI's Evals product within Agent Kit allows developers to test results from non-OpenAI models via integrations like Open Router. This positions Agent Kit not just as an OpenAI-centric tool, but as a central, model-agnostic platform for building and optimizing agents.

OpenAI uses two connector types. First-party (1P) "sync connectors" store data to enable higher-quality, optimized experiences (e.g., re-ranking). Third-party (3P) MCP connectors provide broad, long-tail coverage but offer less control. This dual approach strategically trades off deep integration quality against ecosystem scale.