How to Install / Upgrade: Muse Spark 1.2 is now available on Vercel AI Gateway

Muse Spark 1.2 from Meta is now available on the Vercel AI Gateway. It is a coding-focused update to the previous Muse Spark model. It keeps general capabilities while improving code generation, complex debugging, codebase understanding, and end-to-end developer workflows. It is built for long-horizon work such as generating whole repositories, building out large projects end to end, and sustaining iterative development.

To use Muse Spark 1.2, open the Vercel AI Gateway and select Muse Spark 1.2 as your model. If you already use an earlier Muse Spark model through the gateway, switch the model identifier to Muse Spark 1.2 in your AI Gateway configuration or application settings. Redeploy or restart your app if your setup caches the previous model choice.

Confirm the selected model is Muse Spark 1.2 in the AI Gateway before you run production traffic. Keep general-capability expectations in place, but exercise coding-focused paths such as code generation, debugging, codebase understanding, and longer multi-step developer workflows so you can verify the 1.2 improvements on your own stack. If a call still routes to the previous Muse Spark model, recheck the model name in your gateway config and application settings.