Figma: AI Model Selection in Figma Make
FigmaFigma expanded Figma Make's AI capabilities by allowing users to switch between AI models directly from the prompt box. Starting February 17, 2026, Claude Sonnet 4.6 and Claude Opus 4.6 — both from Anthropic — became available as selectable models within Make, alongside an "experimental models" setting that will surface the latest model releases as they become available. The addition gives designers and non-technical users the ability to choose between a faster model and a more capable one depending on the complexity of their prototype.
Sources & Mentions
3 external resources covering this update
Overview
Figma Make, the AI-powered tool that generates interactive prototypes and mini-apps from natural language prompts, gained a significant new capability on February 17, 2026: multi-model selection. Users can now switch between AI models directly from the prompt box, giving them control over the intelligence powering their Make sessions.
Available Models
The initial rollout includes two new Claude models from Anthropic:
Claude Sonnet 4.6 is described as Anthropic's most capable Sonnet model to date. Internal testing showed that users preferred Sonnet 4.6 over the previous Sonnet 4.5 approximately 70% of the time, and over the previous Opus 4.5 approximately 59% of the time — a strong signal of meaningfully improved output quality.
Claude Opus 4.6 is positioned as the high-capability option for complex, multi-layered tasks. Figma's documentation describes Opus 4.6 as able to "generate complex, interactive apps and prototypes with an impressive creative range, translating detailed designs and multi-layered tasks into code on the first try."
Experimental Models Setting
In addition to the two standard models, Figma introduced an "experimental models" setting. This toggle gives users early access to the latest AI model releases as they become available in Make — including models beyond the Anthropic lineup, such as Gemini 3 Pro. This represents a deliberate multi-model strategy: rather than committing to a single AI provider, Figma is building the platform layer so that model quality improvements flow directly to users without requiring a product update.
Why It Matters
The addition of model selection transforms Make from a fixed-capability tool into a more flexible AI workspace. Designers working on straightforward wireframes or simple UI mockups can opt for faster, lower-cost models, while teams building complex, interactive flows with detailed logic can reach for a more capable model. The explicit acknowledgment that model quality "is a moving target" in Figma's documentation reflects a realistic and forward-looking approach to AI product design.