Open models only: back to school challenge

If you’ve been comparing open weight AI models and providers like us, now’s the time for action, in the form of a challenge. This month, ditch your AI coding subscription and try to spend the whole of September using only the one efficient open weight model: GLM 5.3 Flash by Z.ai. Here’s how, and what to expect.

Why open weight, why GLM 5.3 Flash

The overall strategy is best explained in Mozilla’s Owners, not renters AI strategy. The TL;DR; is you get greater flexibility, more transparency on your usage, and these days pretty much the exact same capabilities.

New efficient models

For agentic coding specifically, open weight models are now so capable that the bottleneck on your results is probably either AI cost or your own expertise. GLM 5.3 Flash specifically is at the very top of the pareto frontier, with benchmark scores at the same level as much heavier models:

Those excellent scores on the Artificial Analysis index combine with excellent usability:

• 1M context window, so any extended coding task is possible.
• Vision support, so it can build off screenshots or QA visually.
• Available across a wide range of providers.

And a very low price which reflects how efficient it is to host this model, based on its size and architecture.

How to switch

We’ve compiled our own opinionated agentic engineering recommendations, for people who want to follow our AI guiding principles. And if you’re not ready to fully switch just yet, try adding the following two tools to your workflow as a way to get started with using models and tools from different providers:

• Open Code Review for AI code reviews.
• AgentsView for usage tracking.

Both work great with existing wokflows. Here’s an example of AgentsView reporting on models in use over 30 days, showing DeepSeek V4 Flash usage across a wide range of tools:

This kind of tool will help you reflect on your AI usage: investigate what’s worked and doesn’t work and get a full picture of your costs.

Try it out and let us know

Those tools are exactly what we’ll be using when trialing Wagtail’s Developer Experience with agent skills, so it’s crucial we can come forward with strong recommendations for our community. And feedback on our plans!

Our first agent skill to upgrade Wagtail sites is a perfect first task. If you take this open weight only challenge this school term, let us know how it goes. And consider talking about your developer process at Wagtail Space 2026, the call for speakers is still open!