Filter and Sort Apps

Managing a large number of serverless apps is now easier with new filtering and sorting controls directly on the apps page.

• Filter by machine type to instantly isolate apps running on specific hardware (e.g., H100, A100, L40) and monitor targeted resource allocation.
• Sort by active runners, GPUs, or queue size to instantly surface the apps consuming the most capacity or backing up with queued requests.

Works in both card view and list view, and stacks with environment and tag filtering so you can find what needs your attention faster.

Aggregate Analytics Components

The Serverless apps page now opens with an aggregate analytics dashboard that summarizes capacity, traffic, and per-app activity across every app you own in one place.

GPU and CPU distribution charts visualize how your active runners are split across machine types (H100, A100, L40, B200, CPU types, etc.)

Live capacity tiles show total Active Runners, Queued Requests, GPUs, and CPUs, each annotated with how many apps contribute to the number

Status code, request traffic, and concurrent request charts plot aggregate request health over your selected window

Top Apps lists your highest-volume apps over the window for quick drill-in

Requests by app is a new stacked chart that breaks aggregate traffic down per app, with a searchable legend you can click to isolate a single app or flip to an Errors view

Legacy CDN Cleanup — June 1st, 2026

On June 1st, 2026, any legacy CDN object not accessed in the past 6 months will be deleted.

How to identify legacy objects

Legacy URLs look like /files/[animal]/[filename] (e.g. /files/otter/AFsfdoliuhhvf.mp4). Anything served from /files/b/... is on our current CDN and is unaffected.

If you’ve accessed it recently, it’s already safe: Any legacy object accessed in the last 6 months has already been automatically migrated to our current CDN — no action needed on your end. The URL is unchanged and the object will be preserved.

To keep a legacy object you haven’t touched in a while: Access it once before June 1st, 2026. That single access triggers the automatic migration and preserves the object. The URL stays the same.

What stays the same

• Legacy URLs continue to work — no code changes needed
• Anything new you create already uses the modern CDN (/files/b/...)

We introduced new aggregate analytics components on serverless app surfaces to keep health signals consistent between the app listing and each app header.

• Shared metrics components now power Runners, Reqs/min, Latency, and Errors in both app cards and app detail headers
• Reqs/min, latency, and error trends are shown with directional indicators using recent activity windows, so regressions stand out at a glance
• App headers now pair those analytics signals with a queue metric, giving a compact operational snapshot before drilling into detailed analytics tabs

Run ComfyUI workflows on fal serverless GPUs without writing a single line of code. Two pre-built zip packages, one double-click — your team is generating on H100s in minutes.

User package

a tiny launcher UI on localhost:9998. Paste your fal API key and the endpoint slug your team lead gave you, click Start, and the full ComfyUI canvas opens on localhost:8188 running against the cloud GPU.

Admin package

a complete management UI on localhost:9999. Add models, custom nodes, and Python deps from a table, set HuggingFace / Civitai tokens for gated weights (auto-pushed to fal secrets at deploy), and ship with one click. Live runner observability, an outputs gallery, and an undeploy switch are built in.

The launcher auto-installs uv and Python 3.11 on first run — no Python knowledge required from end users. Works on macOS and Windows.

Diagnose why a runner was terminated directly from the dashboard. The reason now appears across every runner surface.

Runner detail page

termination reason is shown inline next to the state.

Runner list

surfaces the same reason via a tooltip on the state badge, so you can scan failures without opening each runner

Runner events timeline

event rows display the termination reason as a highlighted badge alongside the status text

Please note that in some cases the termination reason may be unknown. When that happens, no reason badge or tooltip is shown.

We’ve launched a comprehensive Model API Reference — auto-generated documentation for every top model on fal.ai, covering video generation, image generation, audio, vision, and 3D.

Each model page includes:

• Full input/output schemas with parameter descriptions, types, and defaults
• Quick Start code examples in Python, JavaScript, and cURL
• Real prompt-and-output examples pulled directly from the fal.ai playground
• Rich model descriptions with feature breakdowns, comparisons, and technical specs
• Direct playground links to try models interactively

The reference is organized by model family (FLUX, Kling Video, Seedance, Nano Banana, Veo, and more) with a navigation structure that mirrors the endpoint hierarchy. Browse by category or jump straight to any endpoint.

Serverless Analytics API

• New GET /v1/serverless/analytics endpoint lets serverless app owners query time-bucketed analytics across all inbound traffic to their endpoints
• Retrieve request counts, success/error rates, and latency percentiles (p50/p75/p90) for any date range and timeframe
• Ideal for exporting analytics to your own tools like BigQuery, Grafana, or Datadog
• Requires endpoint ownership
• The existing GET /v1/models/analytics continues to show your own request activity as a caller

Notifications Overhaul

Redesigned notification dropdown so you can stay on top of issues without leaving the page you’re on

Category filtering lets you cut through noise and focus on the notification types that matter to you

Pagination so you can browse your full notification history without losing your place

Mark all as read to quickly clear your inbox when you’ve caught up

OOM alerts notify you when a runner runs out of memory, so you can resize before it impacts users

Notification badge on app tabs shows unread counts per app so you know exactly which apps need attention

See notification settings to configure alerts.

Cold Start and Queue Percentiles

Cold start ratio shows what percentage of requests hit a cold start, so you can measure the impact of your scaling configuration

Cold start duration percentiles (p50, p75, p90, p95) help you understand whether cold starts are a minor delay or a real bottleneck for your users

Queue wait percentiles (p50, p75, p90, p95) reveal how long requests wait before a runner picks them up, helping you decide if you need more concurrency

A new startup breakdown card shows exactly where startup time goes (image pull, setup, etc.) so you know what to optimize

The analytics layout has been redesigned with expandable sections so you can focus on the metrics that matter most