- Apr 23, 2026
- Date parsed from source:Apr 23, 2026
- First seen by Releasebot:Apr 24, 2026
Navigate to header Runner Termination Reason
fal adds termination reasons across runner surfaces for quicker failure diagnosis from the dashboard.
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.
Original source - Apr 23, 2026
- Date parsed from source:Apr 23, 2026
- First seen by Releasebot:Apr 23, 2026
Navigate to header fal Workflow
fal improves workflow model search, API docs, node locking, visible node IDs, and overall performance.
fal Workflow
- Improved the model search experience
- Improved API documentation
- Smoother workflow when adding models
- Node IDs are visible in the UI
- Nodes can be locked
- Media-type icons on node handles
- Performance improvements and bug fixes
All of your release notes in one feed
Join Releasebot and get updates from fal and hundreds of other software products.
- Apr 14, 2026
- Date parsed from source:Apr 14, 2026
- First seen by Releasebot:Apr 15, 2026
Navigate to header Model API Reference
fal launches a comprehensive Model API Reference with auto-generated docs for top fal.ai models across video, image, audio, vision, and 3D. It includes schemas, quick starts, real examples, rich model details, and direct playground links in a browsable hierarchy.
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.
Original source - Apr 10, 2026
- Date parsed from source:Apr 10, 2026
- First seen by Releasebot:Apr 11, 2026
- Modified by Releasebot:Apr 23, 2026
Navigate to header Serverless Analytics API
fal adds a Serverless Analytics API with time-bucketed traffic, success, error, and latency metrics for serverless app owners.
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
- Apr 1, 2026
- Date parsed from source:Apr 1, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Latency Percentile Chart
fal adds a latency percentile chart to analytics for p50, p90, p95, and p99 request latency over time.
Latency Percentile Chart
The analytics page now includes a latency percentile chart showing p50, p90, p95, and p99 request latency over time
Quickly spot latency regressions or tail-latency spikes at a glance
Original source - Mar 31, 2026
- Date parsed from source:Mar 31, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Multi-Endpoint Aggregation in Analytics
fal adds multi-endpoint aggregation in App Analytics for unified performance metrics across all endpoints.
Multi-Endpoint Aggregation in Analytics
Select “All” endpoints in App Analytics to see metrics aggregated across every endpoint at once
Aggregation works across request counts, error rates, percentile charts, and gateway stats, so you can get a full picture of your app’s performance without switching between endpoints
Original source - Mar 31, 2026
- Date parsed from source:Mar 31, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header GPU and Runner Metrics on Apps Page
fal adds GPU and runner metrics to the Apps page, with aggregate usage bars and per-app queue and GPU columns.
GPU and Runner Metrics on Apps Page
The apps page now shows an aggregate metrics bar with total runners, queue depth, and GPU distribution, giving you a quick overview of your resource usage without clicking into each app
Per-app GPU and queue columns in both card view and list view make it easy to compare usage across apps at a glance
Original source - Mar 31, 2026
- Date parsed from source:Mar 31, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Logs Endpoint Filtering and Source Column
fal adds logs endpoint filtering and a Source column for easier log tracing.
Logs Endpoint Filtering and Source Column
Filter logs by endpoint to focus on a specific route
A new Source column shows which endpoint or system action produced each log line
Original source - Mar 30, 2026
- Date parsed from source:Mar 30, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Notifications Overhaul
fal releases a notifications overhaul with a redesigned dropdown, category filtering, pagination, and mark all as read. It also adds OOM alerts, unread badges on app tabs, and notification settings to help users stay on top of issues without leaving the page.
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.
Original source - Mar 28, 2026
- Date parsed from source:Mar 28, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Cold Start and Queue Percentiles
fal adds cold start and queue wait percentiles, plus a startup breakdown card and a redesigned analytics layout with expandable sections, helping users spot bottlenecks and focus on the metrics that matter most.
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
Original source - Mar 28, 2026
- Date parsed from source:Mar 28, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Request Throughput Charts
fal adds App Analytics request throughput charts for processed, received and concurrent requests.
Request Throughput Charts
New charts are available on the App Analytics Requests tab:
- Processed requests per second chart shows your inference throughput over time
- Received requests per second chart shows the inbound request rate
- Concurrent requests chart shows how many requests are in-flight simultaneously
- Mar 28, 2026
- Date parsed from source:Mar 28, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header API Key Tags and Editing
fal adds API key tags and dashboard editing for key descriptions to help organize and update keys without recreating them.
API Key Tags and Editing
Tags on API keys let you organize keys with the same tagging system used for apps
Editable key descriptions can now be updated directly from the dashboard without recreating the key
Original source - Mar 27, 2026
- Date parsed from source:Mar 27, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Request Timing Breakdown
fal adds request timing breakdowns in the requests list with startup and execution time details.
Request Timing Breakdown
Request duration in the requests list now shows a breakdown into startup time and execution time
Hover over the duration to see the full timing detail
Original source - Mar 27, 2026
- Date parsed from source:Mar 27, 2026
- First seen by Releasebot:Apr 2, 2026
Navigate to header Environment Manager
fal adds a new environment manager dialog and searchable environment selector for easier environment creation and deletion.
Environment Manager
A new environment manager dialog lets you create and delete environments in one place
The environment selector is now searchable, replacing the old dropdown
Original source - Mar 25, 2026
- Date parsed from source:Mar 25, 2026
- First seen by Releasebot:Mar 27, 2026
Navigate to header Requests Page Overhaul
fal releases a requests page overhaul with interactive status code and p90 latency charts, drag-to-filter time ranges, sortable request metrics, and a direct jump to App Analytics with filters applied.
Requests Page Overhaul
- Status code and latency charts — the requests page now shows interactive charts for request status code distribution and p90 latency over time, giving you an instant picture of your app’s health
- Click and drag to filter — select a time range on any chart to filter the request list below to just that window, making it easy to isolate a spike or incident
- Sort by cold start, execution time, and latency — sort the request list by longest cold start duration, execution time, total latency, and more to quickly surface the slowest or most problematic requests
- Jump to Analytics — a direct link takes you from the requests page to App Analytics with your current filters pre-applied