11 AI models, one prompt: which is worth your credits?
Choosing an AI model: one prompt, 11 models, different results
Netlify now offers access to 11 AI models via its Agent Runners and AI Gateway, including new open models like Kimi K3, GLM 5.2, and DeepSeek V4. To help users choose, they ran identical prompts across all models and compared results, credit usage, and quality. The test reveals a wide cost range—from 2.4 credits for DeepSeek V4 Flash to 519 for Claude Opus 5—with surprising differences in output quality. Opus occasionally overspends but delivers richer designs, while cheaper models like GPT 5.6 Terra offer a different, not necessarily worse, visual style. The full report is available online.
That’s a pretty wide distribution, eh? Not only that: the Claude Opus average is heavily slanted upwards because one of its three runs spent a whopping 1,055 credits!