---
title: "Product updates: Sandbox Sidecars, new models, a refreshed dashboard, and more"
description: "Modal added day-zero support for Kimi K3, Qwen 3.8, GLM 5.3, and GLM 5.3 Flash on Auto Endpoints, with custom DFlash speculators boosting throughput to 460 tokens per second. New environment-level budgets give Team and Enterprise workspaces per-environment compute limits, while the pricing multiplier for broad region selection dropped from 1.5x to 1.15x. The dashboard got a refreshed navigation, color system, and beta light mode, and Private Environments now support a default No Access role. Sandbox Sidecars are in public alpha, running additional containers via low-latency internal networking, and VM Sandboxes are in public beta with a real Linux kernel for Docker and eBPF. Sandbox directory snapshots and a new filesystem API are now GA, and regional Proxies allow selecting a region for static outbound IPs, while SDK updates improved log APIs and autoscaler reporting."
---

# Product updates: Sandbox Sidecars, new models, a refreshed dashboard, and more

[Modal](https://yomu.fyi/company/modal) · Sep 14, 2026

**Type:** Announcement

## Summary

Modal added day-zero support for Kimi K3, Qwen 3.8, GLM 5.3, and GLM 5.3 Flash on Auto Endpoints, with custom DFlash speculators boosting throughput to 460 tokens per second. New environment-level budgets give Team and Enterprise workspaces per-environment compute limits, while the pricing multiplier for broad region selection dropped from 1.5x to 1.15x. The dashboard got a refreshed navigation, color system, and beta light mode, and Private Environments now support a default No Access role. Sandbox Sidecars are in public alpha, running additional containers via low-latency internal networking, and VM Sandboxes are in public beta with a real Linux kernel for Docker and eBPF. Sandbox directory snapshots and a new filesystem API are now GA, and regional Proxies allow selecting a region for static outbound IPs, while SDK updates improved log APIs and autoscaler reporting.

## Takeaways

- Modal provided day-zero support for Kimi K3, Qwen 3.8, GLM 5.3, and GLM 5.3 Flash with custom DFlash speculators, achieving up to 460 tokens per second on agentic workloads.
- Sandbox Sidecars (public alpha) allow running additional containers alongside a main sandbox on the same host with low-latency internal networking, useful for proxies and multi-container workloads.
- VM Sandboxes (public beta) run a real Linux kernel, supporting Docker containers inside sandboxes and Linux features like eBPF, systemd, and cgroups, with better filesystem performance.

## FAQ

### What new models did Modal add support for?

Modal added day-zero support for Kimi K3, Qwen 3.8, GLM 5.3, and GLM 5.3 Flash, all available on Auto Endpoints with custom DFlash speculators for improved throughput.

### What are Sandbox Sidecars and when are they available?

Sandbox Sidecars are additional containers running beside a main sandbox on the same host via a low-latency internal network. They entered public alpha in August 2026 for use as network proxies or for separating agent harnesses from tool execution.

### How do environment-level budgets work?

Environment-level budgets let Team and Enterprise workspace owners and managers set a compute-usage budget per environment and track current-cycle usage against it, providing teams their own guardrails without splitting workspaces.

**Tags:** [AI](https://yomu.fyi/topic/ai), [GPU](https://yomu.fyi/topic/gpu), [LLMs](https://yomu.fyi/topic/llm), [Serverless](https://yomu.fyi/topic/serverless)

- Source: [Modal](https://modal.com/blog/product-updates-sidecars-models-dashboard)
- Source URL: https://modal.com/blog/product-updates-sidecars-models-dashboard
- Ingested by Yomu: 2026-09-20T07:47:20.495Z

[Read original post](https://modal.com/blog/product-updates-sidecars-models-dashboard)