New model: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is now available on a shared endpoint, with options for dedicated deployments.
13 releases · 0 this month
DeepSeek V4.1 Flash is now available on a shared endpoint, with options for dedicated deployments.
When you sign in to the console , you land on a new home page that provides an overview of your plan and usage.
You can now edit the system prompt when you chat with a model in the Playground . Each model remembers your system prompt. To go back to the default prompt, click Reset .
Your profile page now has email preferences for billing alerts, tips, and marketing.
A model endpoint shows more accurate usage: We now report cached input tokens in model usage. FLUX megapixels now appear in model usage.
Now you can set up automatic credit reloading in the Billing page. Enable this so you won't run out of credits in the middle of a job. This applies to users on the Starter plan.
You can now deploy GLM 5.3 as a dedicated deployment in Modular Cloud. For the full list of shared endpoints and dedicated deployment options, see Supported models .
Modular Cloud is now generally available. Sign up and run inference right away on one of our shared model endpoints.
| Release-notes page | Site | Feed |
|---|---|---|
| Mojo releases docs.modular.com | docs.modular.com | None |