Test Builder: 54+ Models & Advanced Generation Engine

Version: 1.9.1, Date: September 15, 2025

Test Builder gets two major upgrades in this release. The model selector has been rebuilt with a three-tier interface supporting 54+ models across OpenAI, Anthropic, xAI, and Google, with real-time cost estimates before you generate. And the prompt generation engine has been upgraded to a modular, multi-strategy architecture with dedicated systems for complexity analysis, format variation, and intelligent strategy selection. Together, these give you far more control and transparency over what model you use, what it costs, and how your prompts are constructed. The rest of this post is grouped by app area.

Test Builder

• New: Enhanced model selector with 54+ models. A three-tier selection interface: choose your AI provider first, then a category (fast and affordable, balanced, premium, or specialized), then the specific model. Each model displays its context window size, capabilities, and recommendations to help you choose the right tool for the job.
• New: Real-time cost estimation. Before you generate, the model selector shows estimated per-request costs broken down by input and output tokens. You can see exactly what each model will cost before committing, making it easy to balance quality against budget.
• New: Multi-provider support. Generate prompts using models from OpenAI, Anthropic, xAI, and Google, all from a single interface. Switch between providers without leaving the builder.
• New: Advanced prompt generation engine. The generation backend has been rebuilt with dedicated components for complexity analysis, format variations, prompt construction, and strategy selection. This produces higher-quality prompts that are better adapted to your specific complexity and output combination.
• New: Format variation system. The engine now supports multiple output format variations, letting it tailor the generated prompt’s structure to different format types rather than using a one-size-fits-all approach.
• Improved: Every available model now includes detailed metadata: context window size, capability tags, cost data, and categorization (fast and affordable, balanced, premium, specialized). It is much easier to compare models at a glance.
• Improved: Test generation operations feed into the enhanced cost monitoring system, so you can track spending across models and optimize your usage over time.
• Improved: The enhanced model selector matches Test Builder’s existing design language with consistent borders, gradients, and responsive behavior. Dropdown menus now have solid backgrounds (no more transparency issues) and the container expands properly when additional options appear.