Releasesby GlyphFallback Chains
Send a primary model and up to two fallback models in one request to POST https://fal.run/execute . If the primary model fails with an error that you allow, fal runs the next model. The response contains the first successful result and a record of each attempt. Each model has its own input, start timeout, and list of errors that start the next model.
Also shipped Oct 29, 2026fal in October 2026 →
Monte Carlo's Terraform provider is now on the OpenTofu registry
Monte Carlo has published its Terraform provider and agent modules to the OpenTofu registry, enabling users to manage Monte Carlo infrastructure as code using OpenTofu.
REST API v2 (Public preview): onboard Monte Carlo from your AI tool, Terraform or a script
Monte Carlo's REST API v2 is now in public preview, enabling automated onboarding and deployment of collection agents via scripts, Terraform, or AI tools.
Gemini-powered Explore summaries in Looker are generally available
The ability to generate summaries of Looker Explores using Gemini assistance is now generally available.
Dashboard relationships are now generally available
Dashboard relationships, which enable multi-fact data models in AI/BI dashboards, are now generally available.
Looker bullet chart visualization is generally available
The bullet chart visualization type is now generally available in Looker, allowing users to evaluate metric performance against targets and thresholds.
Xero connector is available in Beta
The managed Xero connector is now available in beta for Databricks Lakeflow Connect, supporting incremental ingestion of accounting data.
More from falEvery fal release →
Rate Limits for Runner and App Management
fal now limits how often you can list, inspect, shell into, stop, and kill apps and runners. The limits apply to the CLI, the Python SDK, and the REST API. When you exceed a limit, the REST API returns 429 Too Many Requests , and the CLI and SDK return the gRPC status RESOURCE_EXHAUSTED . Learn more about the limits
Key Presets and Custom Policies
Keys now use permission presets instead of the ADMIN and API scopes. When you create a key, select one of seven presets: API , SERVERLESS , DEPLOY , COMPUTE , BILLING , READONLY , or FULL . If no preset matches your case, select the exact permissions the key needs. You can also limit a key to specific models and set it to expire.
Billing Headers for WebSocket Endpoints
Shared WebSocket endpoints can now declare billing on their 101 upgrade response. Set x-fal-billable-units when the unit count is known at connect time. Set x-fal-billable-units-webhook to 1 when the count is only known at the end of the session. Then report the total with POST /requests/billable-units/{request_id} .
Switch Between App Endpoints in the Dashboard Playground
Deployed Serverless apps now include Testing > Playground in the app dashboard. Select an available endpoint, fill in its generated input form, and run a request without leaving the app. Multi-endpoint apps have one place to test their endpoints, using the existing Playground authentication and billing behavior. Open the guide
Platform MCP Server
fal's second MCP server , the Platform API MCP , is now available at https://api.fal.ai/v1/mcp/platform . Where the Run MCP lets your AI assistant build with models , this one lets it operate your fal account : connect Claude Code, Cursor, or any MCP-compatible client with your API key and ask "why did my last request to my-app fail?" , your assistant walks...
GPU Utilization in Runner Telemetry
Runner telemetry now includes a dedicated GPU Utilization chart alongside the existing CPU, memory, and VRAM charts, so you can see how much compute your GPUs are actually doing -- not just how much memory they hold.
Deploy Messages and Annotations
You can now attach a freeform message and custom annotations to each revision when deploying: Messages and annotations are set at deploy time and stay with the revision. View and search them on the app's Versions page in the dashboard, or fetch them via the revisions API .
App-Level Retry Configuration
Apps can now register a default per-condition retry budget at deploy time with the new retry_config deployment option, using the same format as the X-Fal-Retry-Config request header. Set it as a class attribute on fal.App or under the app's table in pyproject.toml .